203 results about "Image domain" patented technology

The invention relates to an underwater image enhancement method based on wavelet Mama, which aims at the problems of color shift, low contrast ratio and fuzzy details of an underwater image, extracts shallow layer features of an underwater low-quality image, inputs the shallow layer features into a multi-scale coding network, and performs joint enhancement on low-frequency color information and high-frequency detail features by using a wavelet Mama unit. Global semantic features are obtained by combining down-sampling layer-by-layer compression, and global modeling of color offset correction and contrast enhancement is completed; the spatial resolution is recovered through up-sampling, and reconstruction and enhancement of texture details and color information are realized in combination with jump connection and a wavelet Mama unit; and finally, the features are mapped to an image domain and fused with input image residual errors, and an enhanced underwater image with natural color, clear texture and balanced contrast is generated. According to the method, frequency domain-space domain joint feature modeling is realized through the wavelet Mama unit, and the color authenticity, the structural definition and the detail perceptibility of the underwater image are remarkably improved.

The invention relates to the technical field of constructional engineering, and discloses a concrete crack intelligent identification and analysis platform based on image and point cloud fusion, the platform operates a concrete crack intelligent identification and analysis method, and the method comprises the following steps: S1, synchronously collecting image data and point cloud data of a concrete structure in the same scene; s2, establishing a unified world coordinate system and generating a depth map corresponding to the image; s3, generating image domain crack candidates; s4, generating a depth domain crack candidate; s5, performing weighted fusion on the image domain crack candidate and the depth domain crack candidate to generate a fusion crack response; s6, extracting a crack skeleton; s7, obtaining a crack three-dimensional model; and S8, selecting an optimal view angle to trigger re-acquisition of the crack area. Through a closed-loop feedback mechanism, an optimal view angle is selected for re-acquisition by calculating a comprehensive utility value after preliminary acquisition, so that information insufficiency caused by illumination, angle or sparse data is effectively made up.

The invention discloses a multi-contrast magnetic resonance image reconstruction method and device based on detail contour feature perception. The method comprises the following steps: acquiring a target modal initial image and an auxiliary modal initial image; constructing an iterative network formed by alternately cascading image domain reconstruction units and data consistency layers, wherein each image domain reconstruction unit comprises an encoder and a decoder; in the first iteration, target modal initial images and auxiliary modal initial images are spliced and then input, an encoder extracts shared features firstly, then global contour features and high-frequency detail features are separated in parallel, and potential features are obtained through collaborative fusion; the decoder takes the potential features as input and outputs an image domain preliminary reconstruction result; the data consistency layer transforms the preliminary result into a k space, performs consistency correction on the preliminary result and a target modal sampling point, and then inversely transforms the preliminary result back to an image domain to complete one iteration; and splicing the current output and the auxiliary modal initial image again, inputting the spliced image into a next round of iteration, and repeating the process until a preset number of times to obtain a final target modal magnetic resonance image.

The invention discloses an unsupervised image conversion imaging method based on the Schrodinger bridge theory, and the method comprises the following steps: 1, constructing an image domain-domain conversion frame based on the Schrodinger bridge theory, simulating a smooth evolution path from a source domain image to a target domain image through a time condition generator, and forming antagonism training in combination with a discriminator; 2, integrating a saliency content guide constraint, a global feature consistency constraint and a contrast learning constraint in the conversion framework so as to enhance semantic content retention and detail generation capability; 3, establishing a composite loss function, and carrying out weighted combination on Schrodinger bridge path loss, adversarial loss and each auxiliary constraint loss for guiding model optimization; and 4, training a time condition generator and a discriminator through an optimization algorithm, and carrying out stable and high-fidelity target domain conversion on the source domain image by utilizing the generator after training is completed. According to the method, the stability of model training and the quality and fidelity of the generated image are remarkably improved.

The invention provides a medical magnetic resonance image reconstruction method and system, and belongs to the technical field of image reconstruction, and the method comprises the steps: obtaining sampling coding and under-sampling k space data; processing the under-sampled k space data through inverse Fourier transform, and converting the k space data into an image domain to obtain under-sampled image data with blurring or artifacts; carrying out preliminary restoration on the undersampled image data based on sampling coding, further applying data consistency operation on the image to obtain a rough image, and taking the rough image as an image condition vector after underspace coding; acquiring a text serving as a cue word, inputting the text into a text encoder, and encoding the text into a high-dimensional semantic embedding vector by the text encoder; and inputting the high-dimensional semantic embedding vector and the image condition vector into a reconstruction model based on the correction flow to predict a full-sampling MRI image, and generating a final reconstructed MRI image.

Techniques are disclosed relating to exchange of images in networked computing applications. In particular, the disclosure relates to exchange of gain curves that are used to represent imaging and / or video in such applications. A gain curve may define a mathematical transformation that relates values from a source image domain to a destination image domain. The image and its associated gain curve(s) may be published to destination devices for consumption. When a destination device consumes the image, the destination device may apply a transform to source image content according to the gain curve(s) published with the image. For example, the destination device may apply a gain curve to an associated image directly, or it may derive another transform from the gain curve and additional information known to the destination device.

Disclosed are methods, systems, and other implementations, including a unified complex-valued deep learning framework (AFT-Net), which determines the k-space domain to image domain mapping for MRI reconstruction and allows incorporation of existing deep learning models. Embodiments include a computer-implemented method for reconstructing images that includes obtaining resonance (MR) k-space data resulting from a scan performed by an MRI scanner on tissue of a patient, with the MR k-space data including complex-valued data, and processing, by a complex-valued machine learning image reconstruction system, the complex-valued data of the MR k-space data to generate image data representing features of the MR k-space data. The processing may include performing data filtering operations, by one or more machine learning filter blocks implemented according to a CU-Net architecture realized using one or more convolutional neural networks (CNN) configured for complex data processing, on data that is based on the k-space data.

The invention belongs to the technical field of cross-seasonal remote sensing image change detection, and particularly relates to a cross-seasonal remote sensing image domain adaptive change detection method based on an improved CycleGAN. According to the method, through segmentation of all models and boundary constraint multi-scale super-pixel segmentation, the source domain image and the target domain image are kept consistent in object-level structure, the problems of ground feature breakage, texture dislocation and sample alignment irregularity caused by seasonal differences are effectively reduced, pre-training ViT-B high-dimensional semantic features and a density clustering algorithm are introduced, and the accuracy and the robustness of the method are improved. Noise samples such as mixed ground features, shadows and illumination anomalies in a complex remote sensing scene can be automatically recognized, a source domain training set is made to be purer, the stability of CycleGAN style migration training is improved, a generator fuses a multi-scale residual block and a self-attention module, a migrated image is made to be close to a target domain in the aspects of color, texture and seasonal features, and the image migration efficiency is improved. And meanwhile, the boundary and the structure of the ground object are kept not to be damaged through semantic consistency constraint, so that the problem of false change in cross-seasonal change detection is fundamentally solved.

The invention discloses a tactile image domain migration method and device based on a multi-scale generative adversarial network, and the method comprises the steps: constructing the multi-scale generative adversarial network, and achieving the domain migration between a simulation tactile image and a real tactile image. The generator takes U-Net as a trunk, introduces a multi-scale stacking module, a multi-stage attention gate mechanism and a channel-space attention module, and improves the reconstruction capability of simulation image textures, illumination and contact areas. And the discriminator adopts a multi-scale discrimination structure to realize the discrimination of image authenticity and detail consistency. Through joint training of joint adversarial loss, loop consistency loss, contact area consistency loss, illumination balance loss and frequency domain loss functions, it is ensured that an output image is consistent with a real image in visual and semantic levels. The method can be widely applied to a robot vision-touch fusion perception task, and the migration performance and robustness of the perception model are remarkably improved under the condition of non-paired data.

The application discloses a vocal cord leukoplakia pathological detection method and system based on a laryngeal endoscope image, a device and a medium, and belongs to the field of data management. The method is as follows: inputting the acquired laryngeal endoscope image into a preset pathological semantic field model, performing feature extraction on the laryngeal endoscope image through the pathological semantic field model to obtain a feature map; performing coordinate mapping on coordinate points of the feature map through the pathological semantic field model, generating a pathological semantic vector corresponding to each coordinate point, and constructing a continuous pathological semantic field according to the pathological semantic vector; deploying a perception particle swarm in the feature image domain, and performing particle iterative motion according to the pathological semantic vector of the deployment position until a lesion contour is generated by meeting a convergence condition, and outputting a vocal cord leukoplakia pathological detection result according to the lesion contour. Therefore, by implementing the application, accurate detection of vocal cord leukoplakia pathology can be realized, and the accuracy and reliability of laryngeal precancerous lesion diagnosis can be improved.

In implementation of techniques for translating images based on semantic information, a computing device implements a translation system to receive an input image in a first format, encoded semantic information describing a domain of the input image, and a selection of a second format. The translation system decodes the encoded semantic information using a machine learning model. The translation system then generates an output image in the second format by translating the input image from the first format to the second format using the machine learning model, the machine learning model guided by the decoded semantic information. The translation system then displays the output image in the second format in a user interface.

This application discloses a method for constructing a dynamic risk map of a vehicle driving environment based on monocular vision, relating to the field of image recognition technology. It addresses the low accuracy and reliability of the final risk map output in existing monocular vision perception technologies due to phenomena such as target jitter, depth hovering, and repeated counting. The method analyzes the ground contact state, contact point coordinates, and foot depth of each target based on a reference support domain. It then projects, temporally fuses, and spatially deduplicates the contact point coordinates based on a projection strategy and foot depth to obtain a set of obstacle candidate points. Furthermore, it constructs a BEV occupancy grid map and a BEV risk grid map. Finally, it generates an image domain risk map based on pixel risk data and the BEV occupancy grid map, and constructs a cognitive risk map. The method outputs the cognitive risk map, the image domain risk map, and the BEV risk grid map, thereby improving the accuracy and reliability of the final risk map output.

The invention provides a polyp image segmentation method based on federal domain generalization and re-parameterization Unet, and belongs to the field of medical image segmentation. Comprising the following steps: S1, preparing different data sources at different clients; s2, constructing a re-parameterized segmentation network at each client; s3, training the segmentation model by adopting federal learning, and executing local updating; s4, a cross-domain generalization mechanism is introduced in the training process, and meanwhile, frequency domain transformation or style disturbance is performed on the polyp medical image, so that the model learns consistent feature representation under different client data distribution; and S5, aggregating the model parameters of each client, and synchronizing the global model parameters to each client.

A sparse helical CT image reconstruction method based on a differentiable helical reconstruction operator. First, actual helical scanning geometric parameters of a subject and corresponding full-angle helical projection data are acquired, and a final reconstructed image is acquired by means of seven steps. In the present invention, actual scanning geometry is used to perform forward projection on a reconstructed sparse-angle image, thereby providing geometric prior guidance for missing projections; moreover, on the basis of the similarity and redundancy characteristics of adjacent projections in helical scanning, a projection completion network is constructed, and by learning bidirectional motion fields of adjacent angles and in combination with geometric prior projections, intermediate missing projection data is jointly synthesized; in addition, the global streak artifact restoration of the image is realized; and finally, the joint training of a projection domain and an image domain is realized, thereby facilitating integral restoration by using projection-image dual-domain information, and data collected within two pitches is used for restoration, thereby effectively avoiding an excessive computational load.

The application discloses a kind of double-layer iteration's image domain target three-dimensional scattering center position extraction method, this method contains: S1, target scattering is modeled and is carried out first layer iteration respectively to obtain the scattering center position of target frequency domain scattering distance direction, azimuth and pitch direction one-dimensional imaging;S2, the data of S1 is combined as target three-dimensional scattering center candidate position, based on target three-dimensional scattering center candidate position carries out second layer iteration and obtains target three-dimensional scattering center position.Its advantages are: this method is based on the scattering center position of target frequency domain scattering distance direction, azimuth and pitch direction one-dimensional imaging target three-dimensional scattering center candidate position, and then based on target three-dimensional scattering center candidate position carries out second layer iteration and obtains target three-dimensional scattering center position, both realize the extraction precision of target scattering center position, and significantly reduce the storage of target overall three-dimensional imaging, improve scattering center position estimation efficiency.

The invention discloses a CBCT (Cone Beam Computed Tomography) projection metal track segmentation and artifact removal method of sparse labeling fine-tuning SAM (Sparse Assisted Modulation), which comprises the following steps: firstly, collecting actual scene data, constructing a data set with lower cost by adopting a sparse labeling mode for SAM fine tuning, and containing metal objects in all shapes as far as possible when collecting the data; then, performing fine adjustment on the SAM, taking the spliced projection frames with different contrast ratios as input during fine adjustment, and taking Mask obtained by image domain threshold segmentation as Prompt; then, directly applying the fine-tuned SAM to actual projection data to predict an accurate projection domain metal Mask angle by angle; then, morphological processing is carried out on the predicted projection domain metal Mask, and triangulation interpolation is carried out on the original projection by using the processed Mask; and finally, carrying out Padding on the interpolated projection to suppress truncation artifacts, and reconstructing by adopting a weighted FDK algorithm to suppress incomplete sampling artifacts to obtain a final metal artifact removed image for subsequent application.

The invention discloses an image reconstruction method and device, electronic equipment and a storage medium, and relates to the technical field of C-arm X-ray equipment and the like, the image reconstruction method is applied to the C-arm X-ray equipment, and the image reconstruction method comprises the following steps: acquiring first truncated projection data; performing projection domain reconstruction on the first truncated projection data based on a projection domain recovery network model to obtain first non-truncated projection data; performing three-dimensional reconstruction on the first non-truncated projection data to obtain a first non-truncated cross-sectional image, and performing image domain reconstruction on the first non-truncated cross-sectional image based on an image domain recovery network model to obtain a first reconstructed image; and carrying out front projection on the first reconstructed image, fusing the first reconstructed image with the first truncated projection data, and carrying out three-dimensional reconstruction to obtain a target image. According to the image reconstruction method provided by the invention, the full information reconstruction of the three-dimensional expanded view of the C-arm X-ray equipment system is realized, and the quality of the reconstructed image is improved.

The invention discloses a phase difference wavefront-image estimation method based on depth image prior. The method comprises the following steps: firstly, constructing a forward physical model of an incoherent imaging system, and generating an observation image with out-of-focus aberration by introducing phase difference; and then using a depth image prior network to jointly optimize image domain loss and wavefront domain loss under the condition of no external training data by taking the consistency of an observation image and a model generation image as a constraint so as to simultaneously obtain a high-quality recovered image and accurate wavefront estimation. The method provided by the invention can realize accurate wavefront estimation and high-quality image recovery under the condition of large aberration under the condition of only needing a small number of acquired images, and has the advantages of strong anti-noise capability, no need of an additional wavefront sensor and low system complexity. The method can be widely applied to fluorescence microscopic imaging and other high-resolution microscopic imaging technologies, and the imaging resolution and the image quality are improved.

The application discloses a low-dose CT reconstruction method and device, relates to the technical field of image processing, and comprises the following steps: acquiring a low-dose CT image; adopting a trained deep learning network to process the low-dose CT image in a projection domain, a chord diagram domain and an image domain respectively; in the projection domain, the low-dose CT image is processed to obtain updated projection data; in the chord diagram domain, the updated projection data is processed to obtain updated chord diagram data; in the image domain, the updated chord diagram data is processed to obtain a reconstructed low-dose CT image; wherein the trained deep learning network takes data of a preset category as a training data set, trains an initial deep learning network, and is obtained by performing intermediate supervision in the training process and fine-tuning the deep learning network in the training. The application can realize good reconstruction of the low-dose CT image.

The disclosure provides a three-dimensional model retrieval method and system based on single-image cross-modal fusion, which relates to the technical field of three-dimensional model retrieval, comprising: acquiring a to-be-queried image and a multi-view three-dimensional model set; inputting the to-be-queried image and the multi-view three-dimensional model set rendered into a trained single-image cross-modal fusion network to output a corresponding three-dimensional model retrieved; the single-image cross-modal fusion network introduces a data exchange process, gives image domain data to an additional channel of a three-dimensional model domain with a set probability, gives model domain data to an additional channel of an image domain with a set probability, and inputs the image domain network and the three-dimensional model domain network after domain feature alignment respectively into a cross-modal network, fuses information of different modalities, and uses a contrast learning to solve the problem of mining of difficult negative samples of triple loss.

The application discloses a kind of simultaneously sparse angle CT reconstruction and metal artifact high-precision correction method, belong to medical imaging field, specifically: simulate the projection data under the influence of beam hardening under sparse angle sampling, obtain sparse sampling and the sinogram of containing metal trace;Interpolation processing is carried out to sparse sinogram, and the sinogram is obtained as the initial sinogram of sinogram domain;According to the additive property of artifact, preliminarily decompose the CT image containing a large number of artifacts, obtain the initial estimated image of image domain and the initial artifact image of artifact domain;A multi-domain optimization model is established, and the constructed multi-domain optimization problem is alternately iterated minimization solution;Iterative update is carried out to sinogram domain, image domain and artifact domain respectively;The high-precision CT image of reconstruction is output.The application can simulate the sinogram containing metal trace and sparse obtained by CT imaging equipment to carry out simultaneously sparse angle CT reconstruction and metal artifact correction, and the reconstruction effect is good and correction precision is high.

This application discloses a SAR imaging method for sea surface ship targets based on inverted conjugate-frequency modulated Z-transform and maximum likelihood estimation, belonging to the field of radar target imaging technology. The method includes: establishing a geometric motion model of the ship target based on its motion; calculating a range-time domain echo signal model based on the geometric motion model; adaptively extracting the echo signal from the echo signal model based on the inverted conjugate-frequency modulated Z-transform; establishing a linear observation equation for phase error using the echo signal to optimally estimate the two-dimensional spatially varied phase error parameters; constructing a compensation function using the optimally estimated two-dimensional spatially varied phase error parameters and performing adaptive iteration based on bandwidth contraction to transform the iterated target signal from the time domain to the image domain, obtaining the final imaging result. This application can effectively eliminate complex two-dimensional spatially varied defocus, improving image resolution and focusing quality.

The invention relates to the technical field of medical image processing. The invention discloses a sparse angle CT (Computed Tomography) reconstruction method and device based on an image domain and a projection domain, which can improve the integrity of feature extraction in a CT imaging reconstruction process. The sparse angle CT reconstruction method based on the image domain and the projection domain comprises the steps that the image domain and the projection domain corresponding to original projection data in CT scanning are obtained, the image domain is a set of image data obtained after the original projection data are processed through a CT reconstruction algorithm, and the projection domain is a set of original projection data; and inputting the image domain and the projection domain into a DU-Net network model, and carrying out parallel processing on the image domain and the projection domain through the DU-Net network model to obtain a target CT image.

The application discloses a CBCT metal artifact removal method and system based on a projection domain metal recognition, which skips a traditional image domain segmentation and orthographic projection process, directly extracts key geometric features of a metal region in original projection images, and realizes high-precision recognition and spatial posture estimation of metal objects by matching with a pre-established metal model library, so that the processing flow is significantly simplified, and the recognition stability and artifact repair effect are improved. In view of the shielding and overlapping problems that may occur in a multi-metal structure, a step-by-step stripping recognition mechanism is proposed, and through round-by-round recognition, fitting and image updating, multi-target interference is effectively avoided, and the accuracy and integrity of model matching are ensured.

The invention discloses a dynamic scene image domain adaptation system and method based on four-dimensional Gaussian sputtering and a computer storage medium, and relates to the field of computer vision and computer graphics, and the method comprises the steps: obtaining dynamic images captured at different time points from a plurality of visual angles; generating a four-dimensional Gaussian model based on the dynamic image; decomposing the four-dimensional Gaussian model into a conditional three-dimensional Gaussian model and an edge one-dimensional time component; extracting a target domain embedding vector; based on the extracted target domain embedding vector and the embedding vector of the three-dimensional Gaussian model, performing affine transformation on each Gaussian point, and mapping the Gaussian representation to the distribution of the target domain; and the multi-view consistency is maintained by predicting the corresponding relationship between different training views. According to the dynamic scene image domain adaptation method based on four-dimensional Gaussian sputtering provided by the embodiment of the invention, the four-dimensional Gaussian is decomposed into the conditional three-dimensional Gaussian and the one-dimensional Gaussian based on time distribution by utilizing extension, so that the multi-view visual consistency can be ensured.

The invention provides a fast generation type screen shooting robust watermarking method and system based on structure perception. The method comprises the steps that 1, original watermarking information is mapped to a high-dimensional continuous submerged space with redundancy characteristics; step 2, constructing a condition-guided watermark residual error generation network, directly mapping the redundant watermark vector to a distribution space of watermark residual error signals under the constraint of image structure prior, and realizing combined control of the amplitude and spatial distribution of the watermark residual error signals; step 3, fast watermark extraction is realized through a multi-stage down-sampling and channel constraint mechanism; and step 4, combining a plurality of continuous illumination field generation mechanisms with an imaging distortion model to construct illumination disturbance of a multi-scene combination. According to the method, the watermark embedding process is converted from the direct optimization of the watermark image domain to the structured modeling of the generative watermark residual error, and the robustness under the screen shooting condition is improved while the calculation complexity is remarkably reduced.

The application discloses a high-precision CT metal artifact correction method based on self-supervised learning, and belongs to the technical field of computer medical imaging, specifically: a data set for training a network is created, and the data set is divided into a training set and a test set; a model-driven image domain subnetwork based on a tight frame, a data-driven sine domain subnetwork based on a Transformer, and a novel coupling mechanism for connecting the two subnetworks are constructed; a loss function is designed for optimizing the coupled model-data double-driven network; the data set and the loss function are used to train and optimize the coupled double-driven network until the training is completed, and an optimal network model is obtained; and the test set image is input into the network model trained in step 3, so that a metal artifact correction image is obtained. The application has high-precision metal artifact correction performance while having a small amount of network parameters, and relieves the demand of the training network for paired CT images.

The application discloses an imaging domain least square migration method, device, electronic equipment and medium, wherein the migration method comprises the following steps: acquiring reverse time migration results and a global space-varying point spread function, and performing regional blocking on the reverse time migration results and the global space-varying point spread function to form a plurality of block data; calculating a spatial domain least square migration result of each block data; and according to a regional blocking mode, reducing the spatial domain least square migration result of each block data to a complete model scale to obtain a global space-varying least square migration result. The application performs regional blocking on the reverse time migration results and the global space-varying point spread function, solves the problem that the space-invariant point spread function cannot effectively consider the space-varying characteristics of the point spread function in the current imaging domain least square reverse time migration, and provides an imaging result with better amplitude fidelity and higher quality, thereby promoting the practicality of the imaging domain least square reverse time migration.