Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2162 results about "Real image" patented technology

In optics, a real image is an image which is located in the plane of convergence for the light rays that originate from a given object. If a screen is placed in the plane of a real image the image will generally become visible on the screen. Examples of real images include the image seen on a cinema screen (the source being the projector), the image produced on a detector in the rear of a camera, and the image produced on an eyeball retina (the camera and eye focus light through an internal convex lens). In ray diagrams (such as the images on the right), real rays of light are always represented by full, solid lines; perceived or extrapolated rays of light are represented by dashed lines. A real image occurs where rays converge, whereas a virtual image occurs where rays only appear to diverge.

Scene reconstruction method based on delayed rendering and three-dimensional Gaussian

The invention provides a scene reconstruction method based on delayed rendering and three-dimensional Gaussian. The method comprises the following steps: S1, generating initial three-dimensional point cloud data based on a multi-view image; s2, constructing a trainable structural body for three-dimensional Gaussian modeling; s3, normal initialization and residual optimization are carried out on the Gaussian ellipsoid primitives, depth consistency constraint is combined, and a differentiable and learnable normal reconstruction mechanism is realized, so that the geometric expression ability of illumination modeling is enhanced; s4, introducing a reflection training mechanism based on ambient light and a reflection direction, and generating a Gaussian attribute based on a visual angle; and S5, a final image is generated through a differentiable Gaussian sputtering rendering algorithm, and optimization is carried out through pixel loss of the final image and a real image. According to the method, the reality sense and geometric consistency of the Gaussian sputtering model under the complex illumination condition are remarkably improved, and the technical problems of unreal rendering effect, inaccurate surface normal estimation, weak propagation capability and the like of the existing three-dimensional Gaussian sputtering model under the complex illumination condition are solved.
Owner:GUANGDONG BOHUA UHD INNOVATION CENT CO LTD

Multi-target scene visual SLAM (Simultaneous Localization and Mapping) method fusing target semantics and Gaussian splashing

The invention discloses a multi-target scene visual SLAM (Simultaneous Localization and Mapping) method fusing target semantics and Gaussian splashing. The method comprises the steps that input data are preprocessed, two-dimensional space masks and semantic information corresponding to the two-dimensional space masks are extracted, global semantic identifiers are distributed to the two-dimensional space masks corresponding to a background and each target, and a target semantic segmentation map is obtained; reading first frame RGBD data as a current frame, acquiring a target semantic segmentation map corresponding to the current frame, and initializing camera pose parameters; respectively establishing an initial target Gaussian splashing model for the background and each target; adopting a Gaussian splash algorithm to render all the target Gaussian splash models to a next frame, and generating an RGB rendering image, a depth rendering image and a target semantic rendering image of the next frame; and designing a loss function between the next frame of rendered image and the corresponding real image, optimizing the pose of the camera, and updating the parameters of the target Gaussian splash model. According to the invention, simultaneous positioning and map construction of multiple target scenes are realized.
Owner:HANGZHOU DIANZI UNIV

Control of an industrial robot for a gripping task

In one aspect, the present invention relates to a distributed system for controlling at least one robot (R) in a gripping task for gripping objects (O) of different types which are arranged in a working area (CB, B, T) of the robot (R). The system comprises a central training computer (CTR), which is designed for pre- and post-training, and at least one local processing unit (LCU), on which real image data of the object (O) is recorded, which is used to generate post-training data.
Owner:VATHOS GMBH

Three-dimensional Gaussian sputtering method for sparse visual angle semantic priori

The invention discloses a three-dimensional Gaussian sputtering method for sparse visual angle semantic priori. The method comprises the following steps of: 1, acquiring a target scene image, constructing a real image set as a data set, and manually selecting an interested object in a target scene to perform semantic three-dimensional reconstruction to obtain an initial semantic image of a sparse view angle; a multi-view image is collected, camera external parameters and scene sparse point clouds are obtained, a plurality of views are selected and input into the SAM2 segmentation model, and a view set Is with semantic images is obtained; 2, using a pre-trained SAM2 segmentation model as an interactive image sequence segmentation model, and initializing a three-dimensional Gaussian primitive according to the scene sparse point cloud; and step 3, training parameters of semantic three-dimensional Gaussian sputtering based on the trained three-dimensional Gaussian sputtering model and the interactive image sequence segmentation model, and reconstructing a target scene. According to the method, the high-quality semantic model is efficiently reconstructed. And the reconstruction result can be easily corrected through the interactive graphical interface in the training process.
Owner:XIDIAN UNIV

Three-dimensional reconstruction method based on fractional gradient optimization and three-dimensional Gaussian sputtering fusion

The invention discloses a three-dimensional reconstruction method based on fractional gradient optimization and three-dimensional Gaussian sputtering fusion. A sparse point cloud is generated through a motion structure recovery technology and input picture data; gaussian primitives with the point cloud as the center are generated in the space; performing rasterization rendering on the scene represented by the Gaussian primitive; carrying out joint optimization function calculation on the rendered picture and the real picture; the fractional calculus is pruned to define and design a fractional order optimizer; optimizing the Gaussian primitive parameters by adopting a fractional order optimizer; and finishing the pruning of the Gaussian ellipsoid according to a self-adaptive pruning strategy. A fractional order optimizer is used for guiding Gaussian primitives to carry out gradient descent, the problem that three-dimensional Gaussian sputtering falls into a local minimum value in three-dimensional reconstruction is effectively relieved through fractional order gradient guidance, and joint loss optimization is carried out on rendered images and real images. The edge information of the image can be better concerned, and a reconstruction scene with richer details can be obtained.
Owner:NANCHANG HANGKONG UNIVERSITY

Deep forgery detection model training method, deep forgery detection method and deep forgery detection system

The invention discloses a deep counterfeiting detection model training method, a deep counterfeiting detection method and a deep counterfeiting detection system, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a training data set containing a real image and a plurality of counterfeit images, and enabling the image to be provided with a label for representing the authenticity; in the training process, the deep forgery detection model can be in contact with various types of image samples, so that wider and more complex image features and forgery modes can be learned, a forgery reason is further marked for a forgery image, and the deep forgery detection model can be helped to deeply understand essential features of forgery content in the training process. Therefore, the problem of insufficient detection capability for well-designed and high-quality counterfeited contents can be solved, and the technical effect of improving the accuracy of counterfeited detection is achieved.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Deep forgery detection method based on visual language model

The invention discloses a deep forgery detection method based on a visual language model, and relates to the field of image forensics. The deep forgery detection method based on the visual language model aims to combine multi-source information to improve the discrimination capability of the model on a real image and a generated image. The method comprises the following steps: firstly, extracting image features through an image encoder of a pre-trained CLIP model; meanwhile, a frequency domain enhanced counterfeit perception adapter is embedded in the image encoder to mine potential anomalies of counterfeit images in the image domain and the frequency domain. Secondly, a manual feature extraction module is provided, discriminative low-dimensional features are extracted from the four aspects of the edge, the texture, the frequency and the symmetry of the image, and the discriminative low-dimensional features are used as auxiliary information input in the forgery detection process, so that the robustness and the interpretability of the model are improved; meanwhile, the text cue words are converted into feature vectors through a text encoder of a pre-training CLIP model; and finally, the model predicts a forgery score by calculating the cosine similarity between the image features and the text features so as to realize the discrimination of the authenticity of the image. According to the method, the problem that the detection capability of the model on the cross-dataset is insufficient is effectively improved.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Multi-feature fusion image forgery detection method based on high-resolution network

The invention discloses a multi-feature fusion image forgery detection method based on a high-resolution network. The method comprises the following steps: (1) training a binary classifier by using a real image and a manipulated image, and storing a model; (2) inputting the image into a pre-trained classifier; calculating the gradient of the image; (3) inputting the generated gradient map and the original image into a feature extraction module to extract gradient features and color space information; the features of the two branches are fused through a convolutional network; (4) inputting the original image into a frequency domain feature extraction block, and extracting high-frequency features of the image; (5) further fusing the fused gradient features and color space features into frequency domain features; a high-resolution network is used as a backbone network in a feature extraction and fusion stage; and (6) the fused features are sent to a discriminator, and whether the input image is real or forged is judged. The method has higher recognition accuracy and robustness, and can be well generalized to unseen counterfeiting methods.
Owner:GUIZHOU NORMAL UNIVERSITY

Deep forgery detection method based on self-mixing

The invention provides a deep counterfeit detection method based on self-mixing, and compared with the prior art, the method generates a mixed image containing counterfeit artifacts by using a self-mixing technology, and carries out the precise detection and recognition of an artifact region of an input image through combining a backbone network OfficientNet-b3 and a counterfeit artifact detection module. The method comprises the following steps of: firstly, performing framing processing on a real image, generating a source image and a target image by utilizing a self-mixing technology, and generating a mixed image with counterfeit artifacts by combining a mask generator with an alpha blowing model; and then, the backbone network extracts global features from the mixed image, and the fake artifact detection module reinforces local feature expression of a mixed region through an artifact space cooperation attention module, so that an artifact region is accurately positioned. And finally, fusing global and local features by using residual connection, and transmitting the fused features to a full connection layer to complete classification. According to the method, various forged image types can be effectively detected, and excellent generalization ability is shown in cross-dataset and unknown scenes.
Owner:GUILIN UNIV OF ELECTRONIC TECH +1

Self-supervised anomaly detection framework for visual quality inspection in manufactruing

An AI-based method for visual inspection of parts manufactured on a shop floor includes acquiring a set of real images of nominal parts manufactured on the shop floor to create training datasets. A self-supervised pre-trainer module is used to pre-train a loss computation neural network in a self-supervised learning process using a first dataset on pretexts defined by real-world conditions pertaining to the shop floor. The first dataset is labeled by automatically extracting pretext-related information from image metadata. A main anomaly trainer module is used to train a main anomaly detection neural network to reconstruct a nominal part image from an input manufactured part image in an unsupervised learning process using a second dataset. The main anomaly training measures a perceptual loss between an input image and a reconstructed image by measuring a difference between feature representations thereof at one or more layers of the pre-trained loss computation neural network.
Owner:SIEMENS AG

Image generation method based on mixed quantum classical condition generative adversarial network

The invention discloses an image generation method based on a mixed quantum classical condition generative adversarial network. The method comprises the following steps: firstly, converting a random condition label and a sample real condition label into one-hot codes, processing input noise and the random condition label by using a quantum circuit, performing measurement to convert a characteristic quantum state into a classical characteristic vector, and obtaining generated image data from the characteristic vector through a classical single-layer neural network. And transmitting the sample real image data and the real condition label into a discriminator to obtain a real image discrimination result, and transmitting the generated image data and the random condition label into the discriminator to obtain a generated image data discrimination result. And calculating discrimination loss based on the two discrimination results, training a discriminator and a quantum condition generator, obtaining a trained mixed quantum classical condition generative adversarial network, and generating a condition image. Based on the above scheme, the problems of unstable classical GAN training and many training parameters are solved, the limitation of the quantum GAN in a condition generation task is broken through, and the application of the quantum generative adversarial network in scenes such as image generation and pattern recognition in the field of real artificial intelligence is further promoted.
Owner:HUNAN NORMAL UNIVERSITY

Image denoising method based on double-branch feature fusion

The invention discloses an image denoising method based on double-branch feature fusion, and the method specifically comprises the steps: 1, carrying out the collection of an image, and carrying out the preprocessing of the collected image; 2, a denoising network with double-branch feature fusion is built, the network comprises a generation network and a discrimination network, and authenticity discrimination is carried out on a denoised image generated by the generation network and a real image through the discrimination network; step 3, adversarial training is carried out on the generative network and the discriminant network to obtain a trained dual-branch feature fusion denoising network; and step 4, performing denoising processing on the image by using the trained generative network. The method is remarkably superior to a traditional denoising method in denoising quality, model generalization ability and operation time, different types of noise can be effectively removed, and more image details and structure information are reserved.
Owner:WUXI UNIV

Rainy day target detection method based on paired image data generation and knowledge distillation

ActiveCN119649328Aincrease training dataEnhance context awarenessCharacter and pattern recognitionBiological modelsPattern recognitionImaging data
The invention discloses a rainy day target detection method based on paired image data generation and knowledge distillation, and belongs to the technical field of automatic driving target detection. The method comprises the following steps: acquiring a real image of a road scene and a semantic segmentation mask; inputting the semantic segmentation mask and the weather condition text information into a trained improved diffusion model to obtain a road scene generation image under a rainy day condition; introducing a CoT module and an ODConv module into the target detection model for optimization, and then improving the target detection model by adopting a dynamic weighted aggregation loss function to obtain an optimized target detection model; performing knowledge distillation to obtain a rainy day target detection enhancement model; and performing target detection by using the rainy day target detection enhancement model. The method provided by the invention is excellent in performance in a rainy day scene, has good generalization ability, can provide higher-precision target detection in various complex scenes, and effectively improves the detection accuracy and stability.
Owner:HUNAN UNIV

Autonomous lifelong SLAM method and system based on visual language model hidden space representation

The invention relates to an introspection lifelong SLAM method and system based on visual language model hidden space representation, and the method comprises the steps: extracting a semantic tag based on an RGB-D image through a semantic encoder, and generating a scene map and a semantic topological graph based on the RGB-D image and the semantic tag; generating a dynamic mask based on the scene map, obtaining a dynamic mask coverage rate, and screening key frames with high static confidence values based on the coverage rate; calculating camera pose estimation corresponding to the key frame in real time, sampling the key frame to realize layering of the key frame, and performing layering rendering by using a NeRF model to obtain a virtual view; the hidden space difference degree of the virtual view and the corresponding real image is calculated, whether error introspection needs to be carried out or not is judged based on the hidden space difference degree, and the system is used for achieving the method. Compared with the prior art, the method has the advantages that open semantic reasoning of VLM, high-precision reconstruction of NeRF and real-time positioning of SLAM are combined, and positioning and mapping accuracy is improved.
Owner:TONGJI UNIV

Pig image BDE reconstruction system and method based on differential image rate filtering

The invention relates to a pig image BDE reconstruction system and method based on differentiatable image rate filtering, and belongs to the field of image processing, and the system comprises an image preprocessing module which is configured to process an original low-bit image; the neural network module acts on the processing and reconstruction tasks of low-bit pig images, the characteristics of each image are collaboratively optimized in a task dividing and conquering mode, and finally a high-quality image is obtained; the loss function module is configured to optimize the network model performance by minimizing the difference between the network output image and the real image; the training module is configured to optimize network model parameters and a learning process by adopting a staged training strategy; and the test and evaluation module is configured to evaluate the image quality through the peak signal-to-noise ratio and the structural similarity index and measure the reconstruction effect of the model. According to the method, a two-stage training strategy is adopted, an image reconstruction task is decomposed into two sub-tasks which cooperate with each other, and spatial resolution enhancement and bit resolution improvement are achieved.
Owner:SICHUAN AGRI UNIV

Human pose recognition using synthetic images and viewpoint / pose encoding

A device receives a real image (e.g., photograph or video frame) that includes a human. The device creates a synthetic image corresponding to the real image. The synthetic image includes a synthetic environment and a humanoid shape that correspond to the human. The device predicts, using a trained viewpoint neural network and based on the synthetic image, a predicted viewpoint heatmap. The device predicts, using a trained pose neural network and based on the synthetic image, a predicted pose heatmap. The device provides, as input to a random synthetic environment, the predicted viewpoint heatmap and the predicted pose heatmap and creates a reconstructed three-dimensional pose based on the predicted viewpoint heatmap, the predicted pose heatmap, and the random synthetic environment. The device classifies the reconstructed three-dimensional pose as a particular type of pose of the human in the real image.
Owner:RGT UNIV OF CALIFORNIA

Method of enhancing abnormal area of ground-penetrating radar image based on hybrid-supervised learning

A method of enhancing an abnormal area of a ground-penetrating radar image based on hybrid-supervised learning includes the steps of: building a database including a real image set, a simulation image set and a simulation image label set; adopting a generative adversarial network; processing semi-supervised training and unsupervised training alternately to obtain a trained model, then inputting a real radar image with abnormal area that needs to be enhanced into the model and processing through the generative network to output an abnormal-area-enhanced image. The method overcomes the problems of differences in characteristics between simulated images and real images, and low utilization efficiency of real image information by unsupervised methods, and improves the utilization efficiency of the enhanced network for real image information, the saliency of abnormal areas on real images, and the generalization ability of the enhanced network, therefore effectively enhances the significance of abnormal areas in ground-penetrating radar images.
Owner:CHENGDU UNIVERSITY OF TECHNOLOGY

Flow field measurement method based on event camera

The invention discloses a flow field measurement method based on an event camera, and the method comprises the steps: generating a PIV data set, each time sequence sample sequence comprising a plurality of frames of continuous particle images, a corresponding velocity vector field, and particle event data at all moments; establishing a flow field data acquisition device based on an event camera and a high-speed camera, acquiring real event data and real image data which are synchronous in time so as to adjust parameters of an event simulator, and verifying and updating particle event data in the PIV data set according to the adjusted event simulator so as to obtain a flow field data acquisition result; obtaining the updated PIV data set as a training data set; building an event camera optical flow method model, and training by adopting the training data set; and on the basis of the trained event camera optical flow method model, event sequences in two adjacent time periods are used as inputs to calculate a velocity vector field corresponding to a middle moment. According to the invention, the flow field velocity field at the required moment can be obtained based on the event data within a period of time.
Owner:ZHEJIANG UNIV

Optical three-dimensional space converter and application based on same

The invention discloses an optical three-dimensional space converter. The optical three-dimensional space converter comprises a long-focus lens, a short-focus micro-lens array and a relative position regulator, one of the two lenses is used for receiving light from an object space and imaging the light into an intermediate image; one is used for converting the intermediate image into a virtual image or a real image of a three-dimensional space; the intermediate image horizontal turner turns the intermediate image left and right in the horizontal direction for real image space conversion; the relative position adjuster is used for adjusting the relative position of the long-focus lens and the short-focus micro lens array. The optical three-dimensional space converter can provide a wide visual field, and the size of an image obtained through compression or amplification of the three-dimensional space converter can be adjusted. The lens can be applied to a wide-view-field real image and virtual image telescope for naked eye observation, a wide-view-field real image and virtual image microscope for naked eye observation, a wide-view-field three-dimensional camera or a wide-view-field three-dimensional projector, an artificial eye and the like.
Owner:SHANGHAI AGAPE MEDICAL TECH CO LTD

Simulation-based synthetic defect generation for visual quality inspection

PCT designated stage expiredWO2025014474A1Image enhancementImage analysisPattern recognitionData set
In a computer-implemented method for supporting vision-based inspection of manufactured parts on a production line, a defect library is created in simulation utilizing real images of manufactured part samples with defects, by digitization and parameterization of enclosed defect geometries of different defect types obtained from the real images. Synthetic defects are generated by randomizing parameters defining the enclosed defect geometries of the defect types in the defect library. A 3D superimposition of the synthetic defects is carried out at randomized positions on a CAD model of a target part to generate a number of defect model objects, each including a digital representation of the target part containing one or more of the synthetic defects. Simulated camera images are then rendered using the generated defect model objects and a digital twin of an inspection environment having one or more cameras, to create a dataset for training a machine learning model.
Owner:SIEMENS CORP

High-precision three-dimensional scene and object reconstruction method, system, equipment and medium

The invention discloses a high-precision three-dimensional scene and object reconstruction method, system, equipment and medium, belongs to three-dimensional scene reconstruction in the technical field of computer vision, and aims to solve the technical problem of low three-dimensional scene reconstruction quality in the prior art. The method comprises the steps of calculating external parameters of a camera, determining coordinates and colors of sampling points closest to the surface of a scene, updating and optimizing parameters and generating a scene geometric model and a rendering graph, the rendering graph is generated based on an SDF MLP network and a Color MLP network in combination with a Gaussian sputtering technology, and parameter optimization is carried out on Gaussian primitives, the SDF MLP network and the Color MLP network by utilizing the generated rendering graph and a real graph. And the Gaussian primitive after parameter optimization, the SDF MLP network and the Color MLP network are utilized to finally generate a high-precision scene geometric model and a new visual angle image with high fidelity rendering quality, so that the technical problem that geometric precision and rendering quality cannot be obtained at the same time in a three-dimensional reconstruction process is effectively solved, and the reconstruction quality of a three-dimensional scene is remarkably improved.
Owner:CHENGDU UNIV OF INFORMATION TECH

Face sketch synthesis method and system based on perception loss

The invention provides a face sketch synthesis method and system based on perceptual loss, and relates to the technical field of image processing, the quality of face sketch synthesis is improved by introducing a strategy based on perceptual loss, high and low frequency features of a face image are extracted by adopting a VGG19 network, and weighted fusion of cross-resolution features is realized through an NSRM module. Therefore, the details and overall perception of the facial features are effectively captured and reserved on different scales, the fineness of the image is improved on the local details, the consistency and the natural sense of the image are enhanced on the global features, the distance between the generated image and the real image in the feature space can be better matched by using the perception loss, and the image quality is improved. And comprehensive optimization is carried out in combination with various losses such as adversarial loss and spectral consistency loss, so that the parameters of the generator and the discriminator are adjusted more efficiently in the training process.
Owner:JIANGXI UNIVERSITY OF FINANCE AND ECONOMICS

Deep forgery detection method and system based on facial embedding difference guidance

The invention belongs to an image processing technology, and particularly relates to a deep forgery detection method and system based on face embedded difference guidance, and the method comprises the steps: generating a forgery image according to an input real image, and calculating a difference image and a semantic difference vector of two images; learning the features of the real image and the forged image by using a first classifier, and learning the features of the real image and the difference image by using a second classifier; splicing and fusing the semantic difference vector and image features extracted from the difference image through a channel to obtain fused features, and learning the difference between the real face features and the fused features by using a third classifier; and calculating the distillation loss between the fusion feature and the image feature of the forged image, and training in combination with the loss of each classifier. According to the method, multi-level feature fusion, a three-classifier architecture and a knowledge distillation mechanism are adopted, the strong generalization ability across data sets is achieved, and the system can output a high-precision deep forgery judgment result.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Road and bridge settlement displacement monitoring system and method based on image detection

The invention discloses a road and bridge settlement displacement monitoring system and method based on image detection, and the method comprises the steps: selecting a plurality of static background reference points in a stable background region of a monitoring scene, so as to construct a virtual and stable image internal reference system; furthermore, by accurately tracking image coordinate changes of the background reference points in the initial reference frame and the current frame, a transformation matrix capable of accurately describing disturbance of the camera from the initial pose to the current pose is reversely calculated, and the transformation matrix is applied to observation coordinates of a monitored target point; therefore, the virtual displacement component introduced by the camera disturbance is accurately stripped from the total displacement, and finally the real image displacement generated only by the motion of the structure is obtained. By means of the mode, the system can effectively resist interference of external factors such as environment vibration and temperature change, it is ensured that the height of the finally calculated physical displacement is close to the real settlement value of the structure, and therefore the accuracy and reliability of the monitoring result are greatly improved.
Owner:HEBEI JITONG ROAD&BRIDGE CONSTRUCT CO LTD

Image forgery detection method based on self-supervised contrast learning

The invention relates to the technical field of image forgery detection, in particular to an image forgery detection method based on self-supervised contrast learning. According to the technical scheme, the method comprises the steps that an image to be detected is input into a trained image forgery detection model, and an image forgery detection result of the image to be detected is obtained; the image forgery detection model comprises a feature extractor which is pre-trained through self-supervised contrast learning and is used for extracting an image feature I of an image to be detected; the classifier is used for classifying the to-be-detected image into a real image or a forged image based on the image features I extracted by the feature extractor; the self-supervised contrast learning pre-training takes a real image set as a positive sample, and takes the real image set and a forged image set as negative samples. According to the method, feature distribution of a real image and a forged image is mined through self-supervised comparative learning, and the problem of generalization of a detection model is solved.
Owner:HANGZHOU ZHONGKE RUIJIAN TECH CO LTD

Image segmentation method for evaluating hepatocellular carcinoma neutron therapy dose

The invention discloses an image segmentation method for evaluating a hepatocellular carcinoma neutron therapy dose, and relates to the technical field of neutron therapy. A 3D U-Net GAN network model is trained through a medical image data set; a generator model and a discriminator model in a 3D U-Net GAN network model are alternately trained by using a real image and a false image randomly generated by the generator model, so that the trained generator model can generate a segmentation result which is more accurate and rich in details for a medical image; the trained discriminator model can more accurately evaluate the authenticity of the output of the generator model, and the trained network can accurately reflect the anatomical structure of the patient, the distribution condition of 10B in the body and the radionuclide dynamics condition when segmenting the medical image, so that the information in the medical image can be accurately and fully displayed, and the medical image segmentation efficiency can be improved. The application is convenient.
Owner:XI AN JIAOTONG UNIV

Sea temperature complementing method and system based on asynchronous diffusion Schrodinger bridge

The invention belongs to the technical field of sea temperature complementation, and discloses a sea temperature complementation method and system based on an asynchronous diffusion Schrodinger bridge, and the method comprises the steps: firstly, generating a weight anomal which reflects the abnormal degree of a pixel through a preprocessing step S1, so as to guide a subsequent diffusion process; s2, establishing a bidirectional diffusion path between the initial complementation image and the real image based on a diffusion Schrodinger bridge theory, and dynamically adjusting a diffusion coefficient according to anomay to generate an intermediate state xt; predicting a score function pred through a U-Net network S3, and reconstructing a current image x0 for updating a state or calculating loss; model parameters are optimized through iteration during training, multi-round denoising reconstruction is carried out during inference, and finally a complete high-quality sea surface temperature image SSTrecon is output. According to the invention, local details are fully reserved, and the accuracy of image completion is improved.
Owner:OCEAN UNIV OF CHINA

Unsupervised domain adaptive semantic segmentation method, system and device based on inter-domain consistency and medium

The invention discloses an unsupervised domain adaptive semantic segmentation method, system and device based on inter-domain consistency and a medium. The method comprises the following steps: translating source domain image data to a target domain style while keeping the content by using a GAN-based multi-scale generative adversarial network; inputting the source domain image data into an inter-domain consistency training network based on a Transform model for adaptive training, wherein the source domain image data subjected to data enhancement is sent to a student network for source domain semantic segmentation training, and an EMA strategy is used for updating a teacher network weight; inputting the target domain label-free image data into a teacher network to generate a pseudo label so as to further guide students to train the network; randomly combining the source domain image data and the target domain image data by using a hybrid strategy to guide students to learn domain invariant knowledge in a network; and finally, adjusting and optimizing the student network according to the consistency of the attention feature map, outputting an unsupervised field adaptive semantic segmentation model, and completing segmentation of target domain image data under the condition of not using a target domain label. According to the method, a model with excellent performance can be trained by using fewer real image data sets in the unmanned driving field, so that the training time and cost are greatly reduced, and the working efficiency is improved.
Owner:XI AN JIAOTONG UNIV

Information processing apparatus and program

An image processing apparatus (information processing apparatus) includes a volumetric image shooting unit (first acquisition unit) that acquires a plurality of real images respectively captured by a plurality of cameras (first imaging devices) arranged around a subject, a volumetric image generation unit (generation unit) that generates a 3D model of the subject from the plurality of real images, and an in-studio image display unit (presentation unit) that presents, to the subject, virtual viewpoint information used in rendering, the 3D model, into an image in a form corresponding to a viewing device.
Owner:SONY GROUP CORP

Titanium alloy microstructure prediction method and system based on conditional generative adversarial network and storage medium

The invention discloses a titanium alloy microscopic structure prediction method and system based on a conditional generative adversarial network and a storage medium, and belongs to the following steps: firstly, constructing a process-structure mapping model, and taking the output of the model as a rule constraint condition; inputting the random noise vector and the rule constraint condition into a conditional generative adversarial network to generate a prediction image; according to the generative adversarial network, thermal dynamic constraints based on physical quantities of microscopic structures are introduced in the training process, so that the interpretability of a prediction result is improved. And carrying out quantitative comparison on the predicted image and the real image, verifying the consistency of the statistical characteristics, and if the verification is passed, outputting a prediction result. According to the method, end-to-end prediction from process parameters to microscopic structure images is realized, the limitation that only symbolization or parameterization prediction can be carried out in a traditional method is broken through, and the intuition, the interpretability and the engineering application value of the method are remarkably enhanced.
Owner:SHANGHAI JIAOTONG UNIV