1403results about "Filling planer surface with attributes" patented technology

The invention discloses a multi-modal semantic and physical law driven remote sensing image generation method, belongs to the technical field of computer vision and remote sensing image generation, and aims to solve the problems of insufficient cross-modal semantic alignment, low reliability of a generation result and insufficient physical mechanism fusion. The four-stage method comprises the following steps: firstly, rejecting low-quality samples from original data and unifying a spatial scale; then, extracting a multi-modal semantic vector by adopting a BLIP model and a CLIP model, and introducing a remote sensing physical rule to carry out vector optimization; then position coding and physical constraint conditions are embedded in the submerged space, and multi-source information joint modeling is achieved through a cross-modal encoder; and finally, by taking text description, physical priori knowledge and diffusion time steps as joint conditions, performing de-noising reasoning based on a Transform architecture, and completing back diffusion reconstruction by means of a trans-attention mechanism. According to the method, physical rationality and semantic consistency are improved, and a more reliable technical normal form is provided for remote sensing image generation in the fields of disaster monitoring, military simulation and the like.

The invention relates to the technical field of image processing, in particular to a glioma area marking method and system for a neuromedical image, and the method comprises the following steps: obtaining a brain nerve image, segmenting a left brain area and a right brain area, carrying out the gray correction, extracting a contour boundary, carrying out the calibration, repairing a broken contour, dividing grids, and recognizing a texture extension path. And matching the transparency level and performing visual rendering to obtain a visual marking result of the glioma region. According to the invention, gray correction is carried out through the symmetry of the brain, the accuracy and the anti-interference capability of boundary point identification are improved by combining a boundary screening mode driven by gray difference, an angle change continuity detection mechanism is adopted, the integrity and the path stability of a curvature structure are enhanced, and a rasterized texture path extraction mode is adopted. And realizing continuous expression of cross-regional texture features, and optimizing a visual hierarchy and detail comparison effect of the marked region in combination with a transparency setting scheme of gray offset matching.

The pattern generation method based on diffusion model fine tuning comprises the following steps: constructing a data set; the generation model comprises an edge detection model ControlNet and a stable diffusion model, the stable diffusion model comprises a text encoder CLIP, a diffusion model U-Net and an image decoder VAE, the CLIP text encoder converts an input natural language into word vector features and inputs the word vector features into a U-Net network in a submerged space, and the diffusion model U-Net and the image decoder VAE are connected with the edge detection model ControlNet and the diffusion model U-Net; the U-Net network is controlled to carry out iterative denoising on pure noise in a low dimension to generate a compressed image, and finally the compressed image is restored to an original pixel image through a decoder VAE, so that text content control image generation is realized; carrying out fine tuning training on the generative model by adopting a LoRA parameter efficient fine tuning technology; and intelligently generating a batik style pattern. The method has the advantages that the texture precision of the generated image can be improved, and the personalized style image can be generated.

The invention discloses a structured data self-learning method based on a graph neural network, and the method comprises the following steps: S1, analyzing structured data, extracting entity fields and relation fields, and constructing a structure candidate graph; s2, generating a node embedding feature matrix, and initializing and recording the adjacency relation of candidate edges; s3, constructing a graph neural network model, inputting node features and an adjacent matrix, and defining a task loss function; s4, evaluating the gradient contribution degree of edge connection by adopting a gradient sensitive sparse adjacency self-learning algorithm, and updating the graph structure representation; s5, introducing an embedded interpretability gradient backtracking mechanism, correcting an edge connection relation and enhancing interpretability; s6, training the graph neural network by using the corrected structure, and updating the node embedding and graph structure; and S7, outputting a final graph structure and an interpretability index, and generating a graph modeling visualization result. According to the method, efficient modeling and explanatory analysis of structured data are realized through a dynamic graph structure learning and gradient backtracking mechanism.

An image processing method, performed by a computer device, comprising: extracting sketch texture features at multiple scales from a sketch image; extracting image noise features at multiple scales from preset noise; determining color guide information corresponding to the sketch image; encoding, for each scale, a noise feature based on a sketch texture feature and the color guide information to obtain multi-scale image features; and performing multi-scale decoding on these image features to obtain a colored image comprising a sketch texture corresponding to the sketch image and a color based on the color guide information. A related training method and apparatus are also provided to develop models for this image processing technique.

The invention discloses a deep learning-based cold resistance evaluation system for medicago sativa L., and the system comprises a data generation module which is used for generating a phenotypic image and corresponding physiological data of medicago sativa L. under low-temperature stress through a diffusion model embedded with plant low-temperature response physical constraints; the evaluation model module is used for extracting cold resistance characteristics from the image and physiological data by adopting a causal-driven dual-channel adaptive network; and the decision module comprises a hierarchical model distillation unit and a federal reinforcement learning unit, and the hierarchical model distillation unit and the federal reinforcement learning unit realize joint training of model compression and decision strategy optimization through an edge-cloud collaborative architecture, output a cold-resistant decision and realize visualization through an augmented reality interface. The method can effectively solve the core problems of traditional medicago sativa cold resistance assessment in the aspects of data generation, model generalization, decision-making efficiency and the like.

The invention discloses a multi-platform-oriented intelligent interface adaptation and rendering optimization method and system, and belongs to the technical field of interface rendering. The method comprises the following steps: firstly, acquiring and analyzing interface description information, and extracting hierarchical structures and constraint relationships of interface elements to obtain abstract description features; performing adaptive layout mapping based on the environment characteristic parameters of the target platform, and dynamically adjusting space occupation and display priorities under the constraint of keeping the relative position relationship of interface elements unchanged to obtain a layout scheme after platform adaptation; determining resource consumption nodes according to interface element distribution characteristics, and determining a layered rendering strategy by analyzing visibility states and updating frequency characteristics; applying the layout scheme and the rendering strategy to a rendering execution process to generate output; and collecting performance feedback data to adaptively update a space occupation and rendering strategy. According to the method and the device, automatic adaptation and rendering performance optimization of the cross-platform interface are realized, and the multi-platform interface rendering efficiency and the user experience are improved.

The invention discloses a remote sensing image semantic segmentation prediction method and system based on a vision-language pre-training model. The method comprises the following steps: acquiring a source domain image with a label and a target domain image without a label; adding a pseudo tag to the target domain image without the tag by using a teacher network; performing style conversion on the labeled source domain image to obtain a style migration image with a target domain image visual style; extracting text embedding features of the labeled source domain image by using a pre-trained vision-language pre-training model to obtain text embedding features of a semantic category; fusing the tagged source domain image, the style migration image and the text embedding features of the semantic category to generate an intermediate domain fusion image containing double-domain information and language priori knowledge; performing random mask processing on the intermediate domain fusion image; and inputting the multi-scale context features and the text embedding features of the student network extraction mask image into a vision-language decoder, and then carrying out semantic segmentation on a prediction result.

The invention relates to the field of intelligent city planning, and discloses a street space quality intelligent evaluation and image generation method and system based on deep learning, and the method specifically comprises the following steps: movably collecting a street space image, and recording the geographic position information; performing perspective correction and multi-view image segmentation on the acquired street image data, and performing spatial matching with geographical location information to obtain a fused image database; and performing semantic segmentation on the image in the fused image database based on a deep learning model, calculating objective and subjective visual perception indexes and facility function indexes of the image, and generating a street space quality evaluation result. The method solves the problems that in the prior art, evaluation dimensions are limited, and an automatic response generation mechanism is lacked, and has the advantages of being intelligent, efficient and comprehensive in subjective and objective evaluation.

The technology introduces 3D Moments, a new computational photography effect. As input a pair of near-duplicate photos is taken (FIG. 1A), i.e., photos of moving subjects from similar viewpoints, which may be very common in people's photo collections. As output, the system produces a video that smoothly interpolates the scene motion from the first photo to the second, while also producing camera motion with parallax that gives a heightened sense of 3D (FIG. 1B). To achieve this effect, the scene is represented as a pair of feature-based layered depth images augmented with scene flow (306). This representation enables motion interpolation along with independent control of the camera viewpoint. The system produces photorealistic space-time videos with motion parallax and scene dynamics (322), while plausibly recovering regions occluded in the original views. Experimentation demonstrating superior performance over baselines on public benchmarks and in-the-wild photos.

The invention discloses an AI exhibition hall control method and system based on crowd thermal distribution monitoring, and the method comprises the steps: obtaining crowd density distribution data, behavior data and environment data through constructing a full-coverage sensing network, employing a thermal imaging camera, a WiFi probe and an infrared sensor, and generating a thermal distribution diagram; through converting discrete density point fusion and labeling into a data set of a continuous thermal field, crowd distribution characteristics are visually displayed, spatial-temporal correlation of crowd flow is effectively modeled by combining a convolutional neural network and a spatial-temporal diagram neural network, a prediction-adjustment-verification closed loop is realized based on a prediction result 6-8 minutes ahead of time, and the prediction efficiency is improved. The control strategy is dynamically adjusted according to the predicted crowd distribution trend and the business target, the guide route or the interaction form can be dynamically adjusted according to the crowd density, the exhibit layout can be adjusted in advance, the number of tourists going back and forth is reduced, the overall flow efficiency is improved, and therefore the display effect of the AI exhibition hall is improved.

The invention discloses an AI diffusion model pattern generation platform and method, the generation platform comprises a visual interaction module, an image generation module and a pattern mapping module, and the image generation module comprises a training sub-module and a reasoning sub-module; the generation method comprises the following steps: preprocessing a text input by a user and an optional structure image, and outputting standardized data; a semantic embedding vector is generated through text coding; carrying out LoRA fine tuning to obtain a style weight module; a ControlNet structure condition is injected; performing diffusion sampling to generate candidate patterns; performing CLIP scoring to screen an optimal pattern; and outputting the optimal pattern and previewing the carrier map. According to the platform and the method provided by the invention, the LoRA low-rank fine tuning, the ControlNet structure condition control and the CLIP similarity evaluation algorithm are fused, so that the effects of customizing the special style pattern with a small number of samples at low cost and accurately controlling the structure and style of the pattern are realized.

The present disclosure generally describe user interfaces related to time. In accordance with embodiments, user interfaces for displaying and enabling an adjustment of a displayed time zone are described. In accordance with embodiments, user interfaces for initiating a measurement of time are described. In accordance with embodiments, user interfaces for enabling and displaying a user interface using a character are described. In accordance with embodiments, user interfaces for enabling and displaying a user interface that includes an indication of a current time are described. In accordance with embodiments, user interfaces for enabling configuration of a background for a user interface are described. In accordance with embodiments, user interfaces for enabling configuration of displayed applications on a user interface are described.

The invention relates to the technical field of packaging image processing, and provides a customizable cultural and creative packaging design system based on AIGC, and the system comprises the following modules: a data input module which is used for receiving cultural and creative themes, cultural element preferences and packaging specification parameters inputted by a user; the culture element database is used for storing multi-dimensional culture symbol data including patterns, color pedigree, historical allusions and semantic association rules; and the AIGC generation engine is used for extracting features from the culture element database according to the input parameters based on a generative adversarial network (GAN) and a Transform model, and generating an initial design draft. 10 versions of high-quality design schemes can be generated within 5 minutes through an AIGC engine, the speed is increased by 8 times compared with a traditional process, meanwhile, the modification feedback period is shortened to 2 hours through AR real-time preview, the user satisfaction degree reaches 94%, the pattern semantic matching accuracy is improved to 89%, the historical allusion misuse rate is reduced to 3% or below, and the design efficiency is improved. And the material waste rate of the automatically generated printing file is reduced to 12%, and the delivery cycle is shortened by 40%.

The invention discloses a Lake and Hunan wood carving image generation method, device and equipment based on a LoRA model and a storage medium, and relates to the technical field of process digitization and image generation, and the method comprises the steps: constructing a Lake and Hunan wood carving manufacturing process feature library based on a material object scanning graph, wood texture data and a manufacturing process video of the Lake and Hunan wood carving; according to the feature library, performing hierarchical training on the initial LoRA model according to a texture layer-cutter layer-pattern layer hierarchical logic to obtain a hierarchical LoRA model, and performing hierarchical fusion on the hierarchical LoRA model and a potential diffusion model to form a lake and Hunan woodcarving image generation model; and analyzing text cue words input by a user by using a keyword system in the feature library, extracting wood carving types, timber texture parameters, folk pattern requirements and scene adaptation features, and inputting the features into the lake and Hunan wood carving image generation model to obtain a target lake and Hunan wood carving image. According to the method, the lake and Hunan woodcarving image with the process reduction degree and the scene adaptability can be generated.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that detects shadows, removes shadows, and synthesizes shadows in a joint-framework. In particular, the disclosed systems access an object mask of an object and a digital image depicting the object and a shadow of the object. Furthermore, the disclosed systems perform object-centered shadow detection and removal to generate a modified digital image without the shadow by utilizing a shadow analyzer model. Moreover, the disclosed systems receive a user interaction to manipulate an object and generate a modified shadow utilizing a shadow synthesis model where the shadow synthesis model is conditioned on a shadow mask generated by the shadow analyzer model.

The embodiment of the invention relates to an image generation method and device, equipment and a medium, and the method comprises the steps: obtaining a first image set, the first image set comprises at least one frame of first image, and the at least one frame of first image comprises a color filling image containing a target role, and / or a line image containing the target role; a second image set is obtained, and the second image set comprises multiple frames of second images corresponding to the multiple three-dimensional angles of the target role; a first animation generation request is sent to a target animation generation model, the first animation generation request carries a first image set and a second image set, and the target animation generation model learns in advance to generate multiple video frames according to the input image set in response to the animation generation request; multiple video frames output by the target animation generation model are obtained, and the multiple video frames comprise multi-angle color filling images of the target role. According to the technical scheme, the animation generation efficiency is improved.

The invention discloses a virtual staining method and system for a pathological section image, and belongs to the technical field of image processing, and the method comprises the steps: constructing a registration data pair for different staining styles through real staining as training data, meanwhile, a virtual dyeing lookup table model comprising a self-adaptive feature encoder, a self-adaptive weight predictor and a basic virtual dyeing lookup table is constructed, and in the model, a feature map and a weight are generated in a self-adaptive mode based on an input original image; the basic virtual dyeing lookup tables are weighted based on the weights to construct the virtual dyeing lookup table for adaptive fusion of the original image, and then the virtual dyeing lookup table is utilized to perform virtual color dyeing of various chemical dyeing styles, so that the dyeing efficiency in the process is high, the dyeing styles can be diversified, and the image quality is improved. The positions and forms of the pixels are not changed, only color values are changed, dyeing is achieved, the dyeing self-adaption is high, the dyeing quality is guaranteed, and the dyeing area has interpretability.

The invention discloses a privacy protection type video fuzzy processing method and device. The method comprises the following steps: S1, detecting a privacy area and a type in real time; s2, predicting a motion track of the privacy area; s3, dynamically adjusting the fuzzy strategy; s4, processing the privacy area; s5, fusing and outputting the protected video; according to the invention, through the multi-mode privacy identification model and optical flow trajectory prediction, the privacy information of the moving target is continuously and accurately positioned, and in combination with sensitivity evaluation, the privacy protection intensity and the video information integrity are balanced under the change of a complex scene; an adaptive fuzzy algorithm is adopted, contour natural transition is reserved, key feature points are only tracked in a privacy area, a fuzzy area is automatically expanded for an emergent high-speed target, and the response requirement of a real-time monitoring scene is met; through a metadata embedding technology, full-link auditing of a privacy processing process is supported, and a sensitive scene threshold value and a boundary extension pixel value enable the system to be flexibly adaptive to different security and protection grade scenes.

This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that utilizes a segmentation approach that distinguishes between smooth-shaded regions from high-frequency regions in an image within a vectorization pipeline to generate a vector image. For instance, the disclosed systems utilize a smoothing function to identify non-overlapping sets of pixels that include locally smooth pixels and pixels with high frequency details for an image. Furthermore, in some instances, the disclosed systems generate separate sets of fill functions (representing color-based regions) using color-based pixel clustering for the non-overlapping sets of pixels. Moreover, in one or more instances, the disclosed systems merge neighboring color-based regions in the sets of fill functions (using color similarity) to generate a set of segmented regions for an image. In some implementations, the disclosed systems utilize the set of segmented regions, from the image, to generate a vector image from the image.

The embodiment of the invention discloses a picture drawing method and device, equipment and a storage medium. The picture drawing method comprises the steps that multiple original pictures uploaded by a user are acquired; the original picture is converted into a to-be-displayed picture to be added in a canvas, the size of the to-be-displayed picture is equal to the to-be-displayed size of the original picture in a viewport, and the viewport comprises an area, displayed in a display screen, in the canvas; a texture image set is created, the texture image set is used for storing the texture of each to-be-displayed picture displayed in the viewport, and the size of the texture image set is determined according to the size of each to-be-displayed picture in the viewport and the position coordinates of the to-be-displayed pictures; drawing the to-be-displayed picture into the texture image set; and drawing the texture atlas into a canvas area in the viewport. According to the technical means, the technical problem that in the related technology, when a user uploads a plurality of pictures in a collaborative drawing board, the collaborative drawing board renders each picture, generated system memory resource occupation is too high is solved.

The embodiment of the invention discloses a method and device for generating a dam surface settlement cloud picture based on a self-adaptive interpolation model. A specific embodiment of the method comprises the steps of performing feature extraction on multi-dimensional monitoring point data of a preset dam structure to generate a dam body scene portrait; according to the dam body scene portrait, generating an optimal interpolation algorithm; optimizing the optimal interpolation algorithm to generate an optimized interpolation algorithm; generating a non-oscillation cloud picture according to dam body physical attributes of a preset dam structure and an optimization interpolation algorithm; performing preset-size grid block division on the non-oscillation cloud picture to generate a cloud picture grid node set; performing parallel processing on each cloud picture grid node in the cloud picture grid node set to generate an accelerated interpolation result; and performing incremental updating on the accelerated interpolation result to generate an updated interpolation result. According to the implementation mode, the accuracy, efficiency and engineering applicability of dam settlement interpolation are improved.

The invention relates to the technical field of deep-sea polymetallic nodule resource assessment methods and systems, provides a deep-sea polymetallic nodule resource assessment method and system, and effectively solves the problems that overlapped areas among polymetallic nodules are easy to cover by silt, are located at the edge parts of the polymetallic nodules, are fused with a seabed background, and are not easy to damage. And complete filling cannot be performed through an expansion algorithm, so that the accuracy of the finally calculated coverage rate is not high.

The invention provides a color filling method and electronic equipment, a first interface is displayed, the first interface comprises a first area and a second area, the color of the first area is a first color, the color of the second area is a second color, and the junction of the first area and the second area comprises M colors, the M colors are different from the first color and the second color; determining P colors according to the second color, the third color and one or more colors in the M colors in response to an operation of filling the second area with the third color by the user; the second color is replaced by the third color, one or more colors in the M colors are replaced by the P colors, and the new color of the junction is determined according to the color to be filled, the color of the seed point and the color of the junction, so that on the basis of ensuring the filling effect, the color transition can be better performed, the sawtooth feeling is reduced, and the filling efficiency is improved. And the drawing experience of the user can be improved.

The embodiment of the invention discloses a camera image editing method and system based on deep learning, and the method comprises the steps: firstly capturing a continuous editing behavior flow and original image data of a user in a camera image editing interface, and then executing dual-mode correlation modeling; generating a user editing preference characteristic spectrum and image editable area sensitivity distribution; then interactive decision reasoning is carried out, an image editing strategy set containing editing tool combination schemes and operation sequence suggestions is output, and each strategy contains at least two editing tool cooperation rules; finally, according to the strategy set and real-time selection of the user, editing parameter adaptation and visual effect iterative optimization are executed, target editing image data are generated, and the intelligence and individuation level and the editing efficiency of image editing are improved.

The invention provides a short play subtitle translation system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the system comprises a subtitle recognition module, an erasing module, a translation module and an output module, and can automatically recognize time information, position coordinates and visual style parameters of subtitles in a short play video. And generating a picture sequence without original subtitles in combination with the erasing processing, and translating the recognized original subtitle text into target language subtitles. The system generates target rendering parameters based on explicit style parameters and implicit style embedding vectors, realizes high restoration of fonts, strokes, shadows, gradient, transparency, textures and dynamic special effects, and performs adaptive adjustment according to target subtitle text features. Therefore, the visual consistency and culture adaptability of translated subtitles are improved in a short drama scene with complicated subtitle styles, frequent dynamic changes and obvious cross-culture differences, the audience impression is improved, and the manual post-processing workload is reduced.

And misjudgment in an inspection system is reduced. The determination device includes: a learned image reconstruction unit that learns so as to reconstruct, from a first mask image obtained by superimposing a mask on an inspection region of a first image, a first image determined to not include a defect, from among images obtained by capturing an object to be inspected, the first mask image being an image obtained by superimposing a mask on the inspection region of the first image, and a second mask image obtained by superimposing a mask on the inspection region of the first image; the mask is overlapped on the inspection area of the first image and is colored according to the type of the material contained in the area corresponding to the inspection object; and a determination unit that compares a second reconstructed image, which is an image reconstructed by inputting a second mask image into the learned image reconstruction unit, with a second image obtained by capturing an object to be inspected, and determines whether or not the second image contains a defect. The second mask image is an image in which the corresponding mask is superimposed on an inspection region of the second image.

The invention provides a construction method of a network structure based on Yolo, and a defect detection method and system. The construction method of the network structure comprises the following steps: replacing attention mechanism modules in a backbone network and a neck network of a Yolo framework with DC3K2 convolution modules; the DC3K2 convolution module is obtained based on improvement of a DSConv module; the method comprises the following steps: adding an up-sampling module in a neck network of a Yolo framework, and splicing the up-sampling module with a DC3K2 convolution module which is not connected with a Concat module in the neck network in a backbone network; a detection head of a small target is added in a head network of a Yolo framework, and the detection head of the small target is connected with an up-sampling module through a DC3K2 convolution module in a neck network. According to the invention, the defect detection precision and the detection efficiency can be effectively balanced in the defect detection process.

The invention discloses an image processing method based on an FPGA, a storage medium and a computer program product, and relates to the technical field of semiconductor manufacturing. The method comprises the following steps: dividing and expanding a wafer image in a memory of an FPGA according to a convolution effective size and an edge effect size, and determining a target effective matrix and a target reading range of the target effective matrix; and obtaining read data according to the target reading range, and obtaining filling data for filling the target effective matrix located at the edge of the wafer image while obtaining the read data. And performing convolution preprocessing on the acquired data according to the pixel data groups corresponding to the target effective matrixes to obtain target data for executing image processing. Based on the pipeline design of caching the wafer image in the memory, positioning the target reading range and obtaining the filling data during reading, the occupation of the cache space of the memory is reduced, the processing delay of the wafer image is reduced, and the overall image processing efficiency is improved.