84results about How to "Improve reconstruction effect" patented technology

The invention discloses a Sentinel-2 remote sensing image super-resolution reconstruction method based on an attention mechanism. The method comprises the following steps: 1, obtaining a Sentinel-2 remote sensing image data set; 2, carrying out the preprocessing of the Sentinel-2 remote sensing image data; 3, randomly dividing the preprocessed Sentinel-2 remote sensing image data into a training set and a test set; 4, constructing a deep learning model structure of the Sentinel-2 remote sensing image super-resolution method based on the attention mechanism; 5, training the built model by using the training set; and 6, testing the test set by using the trained model to obtain a Sentinel-2 remote sensing image super-division image. According to the method, the characteristics of the Sentinel-2 satellite image are fully utilized, and the remote sensing image fusion thought is combined, so that the quality of the super-resolution image is improved, and the accuracy and reliability of the earth surface information are enhanced.

The invention provides a fast magnetic resonance reconstruction method and system based on a multistage wavelet convolution network, and particularly relates to the technical field of magnetic resonance imaging and image reconstruction, and the scheme comprises the steps: collecting multi-channel under-sampling K space data; inverse Fourier transform is carried out on the multi-channel under-sampling K space data to obtain an under-sampling magnetic resonance image; and inputting the undersampled magnetic resonance image into a trained multi-stage wavelet convolutional network for reconstruction to obtain a reconstructed magnetic resonance image, the multi-stage wavelet convolutional network being constructed based on multi-stage wavelet transform and a convolutional neural network. According to the scheme, the magnetic resonance K space data is collected in an undersampling mode, the scanning time can be shortened, the multi-stage wavelet convolution network can effectively reserve high-frequency details of the image in the reconstruction process, and therefore the reconstruction quality and efficiency of the multi-channel magnetic resonance image can be remarkably improved on the whole.

The invention discloses a Transform-based abnormal index prediction method for a water-turbine generator set, and the method comprises the steps: collecting monitoring indexes of multiple dimensions of the water-turbine generator set, enabling the monitoring indexes to comprise temperature, current, voltage, water pressure, water flow, oil pressure and amplitude, carrying out the statistics of the data missing value proportion of the collected monitoring indexes, and carrying out the prediction of the abnormal indexes of the water-turbine generator set. Missing value filling is completed according to the actual storage behavior of the system; a random forest algorithm is adopted, original features of multiple dimensions are screened in combination with the feature cross-correlation matrix, and finally feature information of 10 dimensions is reserved to serve as modeling data input; the method comprises the following steps: constructing a transform model and a generative adversarial network (GAN), and taking the transform model as a generator of the GAN, thereby constructing a TransGAN prediction model; enabling the prediction model to be converged in an optimal state through iterative training; abnormal value prediction is carried out on the collected monitoring data of the multiple dimensions of the water-turbine generator set through the constructed prediction model; the method can improve the detection precision when there is no abnormal value sample.

The invention relates to the technical field of three-dimensional reconstruction, and provides a data synthesis method and a training method for monocular three-dimensional reconstruction based on synthesized data, and the method comprises the steps: 1, rendering a picture containing a specific object into a plurality of pictures I corresponding to the object at different angles; step 2, obtaining a mask m of the object based on the picture I, and 3, guiding the picture generation model to generate a new picture which conforms to the text description and retains the structural information of the specific object by utilizing the picture I by utilizing the mask m and the additionally input text description. According to the method, a large number of 3D models and picture pairs are generated through different viewpoints, styles and background conditions, a rich training data set is provided, and the generalization ability of the monocular three-dimensional reconstruction model can be remarkably improved through the diversity. By randomly applying disturbance within a certain angle range of a plurality of viewpoints (R, T), the adaptive capacity of the model to different camera poses is improved, and the robustness of monocular three-dimensional reconstruction is enhanced.

The invention provides a light field microscope three-dimensional image reconstruction system and method integrated with an event camera, and belongs to the technical field of optics. According to the invention, original light field data is synthesized into event data for training a network, the event data is input into an event image reconstruction network module capable of converting continuous event streams into a series of intensity images to obtain light field event images, and then three-dimensional reconstruction of a target area is obtained through a three-dimensional image reconstruction network module. And a new technical reference is provided for solving the problem of how to improve the three-dimensional reconstruction quality and resolution of the light field microscope.

The invention discloses a scene depth estimation method and device, image processing equipment and a storage medium, and belongs to the technical field of computer vision, and the scene depth estimation method comprises the steps: selecting a single image with shielding, reflection or perspective from a multi-view image set for depth fusion; the improved depth information is spread to other views in a re-projection mode, so that the time overhead is reduced while the reconstruction effect is improved; performing semantic division on the index image to obtain the weight of each semantic factor; the problem that feature points are difficult to match due to a special area is solved by introducing single-view depth estimation; fusing a single-view estimation result and a multi-view depth estimation result under the constraint of semantic information, and spreading the fused result to other view angles in a re-projection manner to obtain a consistent depth estimation result corresponding to the current scene; consistency estimation can be accurately carried out on the depth of each area in the scene.

The invention discloses an ultra-lightweight speech enhancement neural network system and method based on adaptive convolution. The system comprises an encoder; a frequency spectrum compression module, which is used for carrying out dynamic range and frequency dimension compression on a noisy speech frequency spectrum; the self-adaptive convolution attention module is used for carrying out frequency dimension downsampling and feature extraction analysis on the compressed feature map through a self-adaptive convolution layer and time channel attention, and then sending the feature map into an intensifier; the intensifier is a dual-path packet recurrent neural network and is used for modeling sub-band time features and intra-frame frequency features of the voice; the decoder comprises a self-adaptive transpose convolution attention module which is used for performing frequency dimension upsampling and feature reconstruction on the feature map output by the enhancer; and the frequency spectrum expansion module is used for expanding the frequency dimension of the feature map output by the self-adaptive transpose convolution attention module. According to the invention, high-performance speech enhancement can be realized with extremely low calculation complexity.

The invention provides a magnetic resonance image reconstruction method and device, an imaging system and a storage medium, and the method comprises the steps: inputting to-be-reconstructed undersampling K space data into an image reconstruction model, and obtaining a reconstructed image; and the image reconstruction model is trained by taking model training loss value minimization as a target: performing inverse Fourier transform and down-sampling on the full-sampling K-space data to obtain a full-sampling image and under-sampling K-space data, and performing randomization, interpolation and inverse Fourier transform on the under-sampling K-space data in sequence to obtain a frequency domain training image; and fusing an undersampling training image obtained by inverse Fourier transform of the undersampling K space data and an undersampling image obtained by sequentially carrying out multiple times of second downsampling and interpolation on the undersampling training image to obtain an image domain training image, and calculating a loss value of the training image obtained by fusing the frequency domain and the image domain and the full-sampling image. According to the invention, through adaptive filling and reconstruction of the image domain and the frequency domain, efficient, rapid and high-quality magnetic resonance image recovery is realized.

The invention provides a stone surface flaw detection method based on a mask and semantic collaborative optimization diffusion model, and belongs to the field of flaw detection. Inputting the input picture into an encoder to obtain an input representation, and performing Gaussian noise forward diffusion on the input representation to obtain a full noise representation; point multiplication is carried out on each input representation and the mask picture, and then a knowledge extraction network guided by the mask is input to generate a mask representation; inputting the input representation into a semantic guidance enhancement network containing a multi-dimensional feature pyramid to obtain a semantic representation; splicing the full noise representation, the mask representation and the semantic representation, performing back diffusion to remove noise step by step, and decoding to generate a reconstructed picture; inputting the input picture and the corresponding reconstructed picture into a feature extraction network, and calculating to obtain an abnormal score; and sorting according to the abnormal scores and forming an abnormal score list, and feeding back the thermodynamic diagram of the input picture corresponding to the abnormal score list to the user. According to the invention, the flaw detection precision can be effectively improved.

The invention discloses a limited angle projection phase contrast CT image reconstruction method and device based on deep learning. The method comprises the following steps: acquiring limited angle projection data of X-ray phase contrast CT scanning through an equal angle increment strategy; performing flat field correction and dark field correction preprocessing on the limited angle projection data to obtain limited angle projection data before phase recovery; preprocessing the finite angle projection data through a phase recovery strategy to obtain finite angle projection data after phase recovery; cT reconstruction is carried out on the limited angle projection data before and after phase recovery through a filtering back projection strategy, and CT images of limited angle projection before and after phase recovery are obtained; a phase contrast CT intelligent image reconstruction network model is constructed and trained; and performing reconstruction processing on the CT image of the limited angle projection before and after phase recovery through the trained phase contrast CT intelligent image reconstruction network model to obtain a reconstructed phase contrast CT image. According to the method, phase contrast CT image reconstruction can be rapidly and efficiently carried out, finite angle reconstruction artifacts can be effectively inhibited, and the image quality is improved.

The invention provides a data resource collecting and labeling method based on big data mining, and relates to the technical field of data collecting and labeling. The method comprises the specific implementation steps of collecting multi-view traffic images, traffic flow data and vehicle speed data of a target road section in real time, preprocessing the multi-view traffic images, and dividing the multi-view traffic images into traffic image groups according to a time sequence; secondly, calculating a traffic concentration index in the first view angle traffic image, identifying a blocking region, mapping the blocking region to another view angle traffic image, and performing congestion labeling; then, through projection of an overlapped detection frame and traffic element point cloud calculation, a traffic accident is marked in combination with a vehicle sag detection model; and finally, environment consistency verification and annotation conflict verification are carried out on a congestion annotation result to ensure the accuracy and integrity of the data. According to the method, the processing accuracy of the traffic data is improved, effective support is provided for traffic management and decision making, and the operation efficiency of an intelligent traffic system is optimized.

The invention discloses an intelligent rapid magnetic resonance imaging reconstruction and pathological positioning method. The method is specifically implemented according to the following steps: step 1, constructing a pathological focused nuclear magnetic resonance image reconstruction model; 2, constructing a pathological focused nuclear magnetic resonance image reconstruction network according to the pathological focused nuclear magnetic resonance image reconstruction model constructed in the step 1; step 3, training a pathological focused nuclear magnetic resonance image reconstruction network; and step 4, using the trained pathologically focused magnetic resonance image reconstruction network to carry out magnetic resonance imaging and pathology positioning. According to the method, dependence on an accurate pixel-level label can be reduced, the pathological part of the image can be positioned while the reconstruction effect of the nuclear magnetic resonance image is enhanced, a better reconstruction effect is achieved on the part, and a clinician is effectively assisted in diagnosis.

The invention discloses an image reconstruction method, system and device for hyperspectral compressed sensing and a medium, and relates to the technical field of hyperspectral image reconstruction. The method comprises the following steps: acquiring a target hyperspectral image; preprocessing the target hyperspectral image to obtain measurement data input by a matching model; inputting the measurement data into a trained reconstruction model for integration to obtain a reconstructed hyperspectral image; the reconstruction model comprises a spatial convolution modulation module, a high and low frequency domain feature integration module and a set optimization objective function; the reconstruction model is determined by training according to a set iteration round, an initialized learning rate and a loss function. According to the method, the high-frequency features and the low-frequency features can be combined by using the frequency branches and the residual enhancement branches, so that the learning ability and the reconstruction effect of the model are enhanced.

The present invention discloses a method for forecasting the continuous distribution probability of extended-period precipitation by integrating fine terrain features, including: obtaining standardized multi-member multi-factor forecast data of the extended-period numerical model ensemble forecast system and regional historical long-term series precipitation observation data, and extracting the continuous distribution characteristics of historical precipitation; obtaining a descaled key terrain multidimensional feature factor library based on regional high-resolution fine terrain data; constructing an extreme gradient boosting U-Net hybrid deep learning precipitation probability forecast model, and carrying out model training and optimization; using the trained model to generate an improved forecast result of the continuous distribution probability of extended-period precipitation. The present invention integrates fine terrain data, adopts a weighted cross entropy loss function, effectively handles the problem of imbalanced precipitation distribution categories, improves the generalization ability of the model, and improves the forecast performance of the continuous distribution probability forecast of precipitation, which has extremely high application value.

The local super-resolution reconstruction algorithm based on the transmission line insulator infrared image includes the following steps: Step 1, image recognition; Step 2, image segmentation; Step 3, super-resolution reconstruction; By using the improved adversarial network structure, unsupervised reconstruction is adopted, the RRDB network structure is adopted, when the network structure is deepened, the stability of training can be maintained, the calculation amount and the use of memory are reduced, and the reconstruction effect is improved, the SeNET attention mechanism is added, from the feature channel level, according to the importance, the useful features such as the outline and the details of the insulator are improved, and the features which are not useful for the program are suppressed. The resolution of the current transmission line insulator infrared image is low, and when the insulator detection is carried out, the workload is large and the problems such as false detection and missed detection occur.

The invention discloses a blueberry tree branch segmentation method and system, and the method comprises the steps: carrying out the multi-scale feature extraction of a to-be-segmented blueberry tree image, and obtaining the feature representation containing low-layer details, middle-layer semantics and high-layer context; information complementation and semantic alignment of deep and shallow layer features are realized through a bidirectional cross-level information interaction module, and fusion features are optimized by using a space and channel attention mechanism to obtain enhanced features; and performing up-sampling and dynamic reconstruction on the enhanced features by adopting a frequency domain dynamic convolution module, refining branch edges and texture details, and outputting a high-resolution pixel-level segmentation result. The method effectively solves the problems of fuzzy boundary, fracture adhesion and background interference in the segmentation of the slender branches and trunks of the blueberries, and has good precision and generalization ability.

The invention discloses a radar signal PRI sequence reconstruction method based on trend filtering, and the method comprises the steps: firstly constructing a PRI sequence filtering model, proposing a maximum posterior probability estimation problem, then updating model parameters through employing an E-M algorithm, solving the maximum posterior probability estimation problem, obtaining PRI sequence filtering results, fusing the obtained PRI sequence filtering results, and carrying out the reconstruction of the PRI sequence. And finally, performing interpolation correction on the PRI sequence, and outputting a final reconstruction result of the PRI sequence. The PRI sequence probability model provided by the method has better capability of expressing radar signal PRI features, can effectively reconstruct radar signal PRI sequence patterns containing abnormal values, remarkably improves PRI sequence reconstruction performance, has important significance in the field of radar signal receiving and analysis, and has good application prospects. The method is suitable for PRI parameter reconstruction of a non-ideal detection signal sequence under false pulse and leakage pulse conditions.

The invention discloses an image super-resolution method based on hierarchical perception distillation. The method comprises the following operation steps: step 1, inputting a low-resolution image data set; 2, a shallow feature extraction process; 3, a deep feature extraction and enhancement process: processing the image through a deeper network layer to extract complex high-level features; step 4, image reconstruction and optimization: after feature extraction and enhancement, the model integrates the extracted features; and 5, outputting a reconstruction result: outputting the processed and reconstructed image as a high-resolution version, wherein the output result shows significant visual improvement. Compared with the prior art, the method has the advantages that the network structure of the super-resolution reconstruction model is optimized, and the advantages of the convolutional neural network and the visual transformer are combined, so that the model which is lighter and more efficient is developed.

A lightweight image super-resolution method based on dynamic reparameterization includes: S1 inputting a preprocessed low-resolution original image into a CNN-based lightweight image super-resolution backbone network and image reconstruction module to obtain a super-resolution image; S2 calculating a loss function based on the super-resolution image and the corresponding high-resolution original image after preprocessing, and updating the network weights through backpropagation; S3 expanding the convolutional layer with the largest contribution score in the iteration cycle into an enhanced edge-oriented reparameterization branch module according to the iteration cycle and initialization conditions, and pruning all reparameterization branches with the smallest contribution score that have been expanded into reparameterization branch modules in the iteration cycle; repeating steps S1-S3 until the backbone network converges. This method improves reconstruction performance without changing the lightweight network parameters of the backbone network and maintaining fast inference speed. Compared to other reparameterization methods, it can significantly reduce training time and memory consumption.

The method belongs to the technical field of panoramic monitoring of ultra-high voltage converter station, and aims to solve the problem that panoramic monitoring image data is directly uploaded to the cloud, occupying a large amount of cloud resources. By adopting multi-scale convolution blocks in the deep multi-scale residual network model to construct low-order and high-order features of images of various scales, the incomplete phenomenon of image detail extraction is avoided, and the residual learning mechanism is adopted to retain low-order rough features, thereby improving the reconstruction ability of the image. Topology optimization constructs the topology structure of the heterogeneous network, and the framework combining deep reinforcement learning and Monte Carlo tree search is used to construct the network according to the pre-defined topology rules. The search result of the Monte Carlo tree strengthens the learning of the deep convolutional neural network, so as to obtain more accurate prediction in the next iteration. After the data is processed in the edge side, it is transmitted to the cloud storage, saving the cloud storage space and transmission bandwidth.

This invention relates to a super-resolution reconstruction method for UAV images of kiwifruit sunburn. Compared with existing technologies, it solves the problems of poor model generalization due to the lack of accurate modeling of the actual physical degradation of UAVs, and the difficulty of feature extraction networks in simultaneously considering global semantics and local high-frequency lesion details, resulting in blurred reconstruction. The invention includes the following steps: acquisition and preprocessing of UAV images of kiwifruit sunburn; generation of multi-scale paired datasets; construction of a super-resolution reconstruction model for kiwifruit sunburn images; training of the super-resolution reconstruction model for kiwifruit sunburn images; acquisition and preprocessing of UAV images; and super-resolution reconstruction of UAV images. This invention significantly eliminates boundary artifacts in image processing by constructing a multi-scale attention and spatial-frequency fusion mechanism, accurately restoring the high-frequency edge texture details of small lesions at different scales, and reducing data acquisition time.

The present invention discloses a super-resolution reconstruction method based on blackboard features in an online classroom scenario. The steps of the super-resolution reconstruction method are as follows: a blackboard photo is taken by a camera set up in the classroom, and the blackboard writing area is accurately extracted using a target detection model, and then image super-resolution reconstruction processing is performed. In addition, for the blackboard writing content with obvious edge features, gradient constraints are introduced in the super-resolution model to strengthen feature learning, effectively improve the resolution of the blackboard writing content, thereby improving the students' learning efficiency in class. The method has the characteristics of fast running speed, low cost, and easy use, ensuring the smooth progress of online live teaching in campus classrooms.

The invention belongs to the technical field of computer vision, and particularly relates to a remote sensing image arbitrary-scale super-resolution reconstruction method based on AGFI and CFUM, and the method comprises the steps: obtaining low-resolution remote sensing image data, and training a remote sensing image arbitrary-scale super-resolution network model; the trained remote sensing image arbitrary-scale super-resolution network model is adopted to realize remote sensing image arbitrary-scale super-resolution reconstruction; the remote sensing image arbitrary scale super-resolution network model comprises a feature extraction module, a feature interaction module and a two-stage up-sampling module; the remote sensing image reconstruction precision can be improved.

The invention relates to the technical field of image processing and financial science and technology, and discloses a face skin color reconstruction and restoration method, device, equipment and medium in an image, and the method comprises the steps: obtaining a face video of a pre-selected model, extracting face images in the face video, obtaining a face image set, and storing the face image set in a database; identifying face key points of each image in the face image set, performing face alignment on the images in the face image set according to the face key points to obtain a pre-processed face image, performing face reconstruction on the pre-processed face image by using a pre-trained face reconstruction model to obtain a reconstructed face image, and performing color space conversion on the preprocessed face image and the reconstructed face image to obtain a converted face image and a converted reconstructed image, and performing color weighted mean fusion on the converted face image and the converted reconstructed image based on a color channel to obtain a target face skin color.

The invention discloses a double-layer sampling medical image pre-training method and system based on mixed distribution, which combine a center cutting strategy based on Gaussian distribution and a mask selection strategy based on local gradient direction distribution and are used for improving the precision of medical image pre-training and segmentation. According to the Gaussian distribution center cutting strategy, cutting is carried out by using a reference center point conforming to Gaussian distribution, so that a cutting area is more concentrated on a main part of an image; and a mask selection strategy based on local gradient direction distribution effectively selects a foreground part with a large amount of information in the medical image by capturing shape features of the image, so that the understanding and analysis capability of the model on key features of the image in a mask reconstruction process is improved. Experimental results show that the method of the invention significantly improves the precision and reliability of medical image segmentation.

The embodiment of the present application discloses a method, chip, device and electronic device for image processing, which uses an image processing neural network to reconstruct the original image to obtain a super-resolution image; wherein the image processing neural network is a UNET network obtained based on a differentiable neural network structure search, wherein the first downsampling module and the corresponding first upsampling module are connected through a shuffled attention module. In this way, when the UNET network is used for image reconstruction, it is possible to combine deep-level features with shallow-level features, refine the image, and improve the reconstruction effect of the super-resolution image. Each layer of the shuffled attention module performs channel attention and spatial attention learning on the feature map data from the encoder, realizes selective reuse of the channel dimension and the spatial dimension to enhance the attention feature, further optimizes the image processing neural network, and improves the network performance and the reliability of the image super-resolution results.

The present application discloses a method, device, electronic device and storage medium for reconstructing a three-dimensional face, and relates to the technical field of electronic devices. The method comprises: obtaining shape parameters and texture parameters of a face to be reconstructed, inputting the shape parameters into a first model, obtaining a three-dimensional face shape output by the first model, inputting the texture parameters into a second model, obtaining a face texture map output by the second model, wherein at least one of the first model and the second model is obtained based on training of a generative adversarial network, and a target three-dimensional face is generated based on the three-dimensional face shape and the face texture map, wherein the target three-dimensional face includes texture information generated based on the face texture map. The present application generates a three-dimensional face shape and / or a face texture map through a trained generative adversarial network, so that the generated target three-dimensional face has rich detail features, thereby improving the reconstruction effect of the three-dimensional face.

The invention relates to the field of computer medical image processing, and provides a semantic perception-based high-quality decayed tooth image synthesis method, which comprises the following steps of: 1, preparing a data set; and step 3, performing high-quality decayed tooth image synthesis on a to-be-predicted CBCT image by using the semantic perception-based synthesis network framework which is trained and optimized in the step 2, and adopting the data set in the step 1 to perform training optimization on the semantic perception-based synthesis network framework. The method is easy to implement, focuses on key tissue boundaries of dental caries diagnosis, and enhances details of a focus area and a dental pulp area. According to the invention, the decayed tooth image quality can be effectively improved, and the risk of decayed tooth misdiagnosis caused by image blurring and artifacts in medical auxiliary diagnosis is reduced. By applying the method, the problem of low quality of the decayed tooth image in oral medicine auxiliary diagnosis can be relieved, and an accurate diagnosis basis is provided for diagnosis of doctors.

This invention discloses a method for reconstructing the surface environment of exoplanets based on a neural radiation field. The method includes: acquiring images of the exoplanet's surface within a visible area using a navigation camera on an exoplanet rover; calculating the camera's intrinsic and extrinsic parameters during imaging based on the common viewpoint matching relationship of the images; constructing a neural radiation field model using the images and the camera's intrinsic and extrinsic parameters as input to reconstruct the exoplanet's surface environment structure; and using the intrinsic and extrinsic parameters corresponding to the new perspective image to be synthesized as input to the neural radiation field model to synthesize a new perspective image or virtual reality image of the exoplanet's surface environment. This method overcomes the disadvantages of exoplanet surface images, such as single and repetitive texture features, sparse and dispersed viewpoints, and low overlap areas, achieving a reconstructed exoplanet surface environment with excellent visual effects and correct geometric structure.

The embodiment of the present application discloses a method, chip, device and electronic device for image processing, which uses an image processing neural network to reconstruct the original image to obtain a super-resolution image; wherein the image processing neural network is a UNET network searched based on a differentiable neural network structure; wherein the first downsampling module and the corresponding first upsampling module are connected through a channel attention module. In this way, the UNET network can be used to combine deep-level features with shallow-level features, refine the image, and improve the reconstruction effect of the super-resolution image. Each layer of the channel attention module performs channel learning on the feature map data from the two layers of downsampling modules in the encoder, enhances the attention to channel features, realizes selective reuse of channels, and further improves the performance of the image processing neural network and the reliability of the image super-resolution results.