2689 results about "Background image" patented technology

Provided are an anomaly detection method and system for multi-source heterogeneous data, an electronic device, a vehicle, a computer-readable storage medium, a computer program product, and a computer program. The method comprises: performing statistical modeling on multi-source heterogeneous data, and obtaining background distribution features of multi-source heterogeneous data distribution through a data splitting method; preprocessing the background distribution features by using a preset sliding window to obtain a background image sequence on a specific time series; on the basis of the size of a target in the background distribution features, performing adaptive partitioning on the background image sequence to obtain an adaptive partitioning result, and identifying single source points of each partition in the adaptive partitioning result through a decoupling representation method; and on the basis of the identified single source points, determining the location of anomalous data in the background image sequence, and on the basis of a comparison calculation result of the multi-source heterogeneous data and the background image sequence from which the anomalous data is removed, obtaining an anomalous data location of the multi-source heterogeneous data.

Systems and methods are described for inputting text input to a trained machine learning model; generating, using the trained machine learning model and based on the text input, a single-layer image comprising a plurality of objects; segmenting the single-layer image to generate a plurality of images, each image of the plurality of images comprising a depiction of a respective object of the plurality of objects of the single-layer image; extracting, from the text input, a portion of the text input describing a background portion of the single-layer image; generating, using the trained machine learning model and based on the extracted portion of the text input, a background image; and generating the multi-layer image based on the plurality of images and the background image.

The invention relates to the technical field of image data processing, and discloses a few-sample scene-oriented industrial product surface defect image analysis method, which comprises the following steps of: obtaining surface gray level image data of a product to be analyzed, calculating a structure tensor matrix and generating an anisotropy degree graph; searching similar blocks in a preset search neighborhood, and constructing a local texture data matrix; performing singular value decomposition on the local texture data matrix to extract a main subspace; constructing a projection operator and utilizing the projection operator to carry out orthogonal projection reconstruction on the local image block to generate a reconstructed background image block; according to the method, through an orthogonal subspace projection mechanism, good product textures and defect signals are separated, random noise is removed, meanwhile, high-frequency structural features are completely reserved, and the method is high in robustness, high in robustness and high in robustness. And the defect detection precision of a complex texture surface in a few-sample scene is improved.

The invention belongs to the technical field of image generation, and particularly discloses a multi-modal scene fusion method based on a large diffusion model. Firstly, singular value decomposition is carried out on a weight matrix of a diffusion model backbone network to update the weight matrix of the backbone network; then, inputting the text cue word into the diffusion model to generate a text condition image; performing VAE decoding and preprocessing on the text condition image to obtain a preprocessed text condition image; inputting the preprocessed text condition image into a pre-trained visual classifier to predict the category, and obtaining a prediction label; updating loss is calculated according to the predicted label and the real label, parameters of the diffusion model are updated, and fine adjustment of the diffusion model is achieved; and finally, generating a scene fusion image by using the fine-tuned diffusion model. Scene fusion is divided into two stages, in the first stage, a combined noise image is generated by sampling a background image and a foreground image, and in the second stage, a scene fusion image is generated through iteration of the combined noise image. According to the method, image generation is guided through the image, seamless fusion of the foreground image and the background image is achieved, meanwhile, image generation is guided through control information, and controllability of scene fusion is enhanced.

A data processing system implements receiving, via a user interface of a client device, images for generating a collage image; generating captions for the images; constructing a first prompt by appending the captions to a first instruction string including instructions to a generative language model to extract a theme from the captions; providing the first prompt to the generative language model and receiving the theme therefrom; constructing a second prompt by appending the theme to a second instruction string including instructions to a text-to-image model to use the theme to create a background image with placeholders; providing the second prompt to the text-to-image model and receiving the background image therefrom; identifying the placeholders in the background image; creating the collage image by fitting the images into the identified placeholders; providing the collage image to the client device; and causing the user interface to display the collage image.

Systems and methods are provided for generating a flat garment pattern and / or 3D mesh representation of a garment from one or more images depicting the garment laid flat or hung up. A system may obtain both a front image depicting a front view of a garment and a back image depicting a back view of the garment. A front and back silhouette of the garment may then be generated, which may include segmenting the garment depiction from background image content. A parametric representation of the garment may then be generated based on the front and back silhouettes, which may be implemented by iteratively optimizing, using differentiable rendering techniques, a garment representation within a parametric garment space previously learned for the particular garment type. A 3D mesh garment representation may then be generated based on the parametric representation, from which a flat sewing pattern may subsequently be generated if desired.

The invention provides a low-visibility environment pedestrian detection method based on an improved YOLOv8n model. A double-branch fusion attention network is adopted in a backbone network of an original YOLOv8n model, and a CBFuse module and a CBLinear module are introduced for feature fusion between different branches; a feature aggregation and calibration pyramid network is introduced, multi-scale feature fusion is carried out through an up-sampling module, a down-sampling module and a feature aggregation and calibration module, and the feature aggregation and calibration module carries out feature calibration and enhancement through a local attention mechanism, a global attention mechanism and a pixel attention mechanism; an adaptive task alignment detection head is introduced to execute a dynamic convolution mechanism, a task decomposition mechanism and a dynamic feature alignment mechanism; an improved YOLOv8n model is formed based on the improvement and serves as a foggy day pedestrian detection network model; according to the method, the detection accuracy and stability of the network in processing shielded and background complex images can be enhanced, and the boundary and detail features of a fuzzy target can be extracted more accurately in low-visibility environments such as foggy days and the like.

The invention relates to the technical field of data generation of sparse scenes, and discloses a data set generation method and system of a sparse scene, and the method comprises the steps: inputting an image which is actually collected by a target sparse scene into a target detection model, and obtaining a detection frame of a target foreground and a background; using a preset segmentation large model to take the detection frames of the target foreground and the background as cue words to perform model reasoning, respectively obtaining masks of the target foreground and the background, and obtaining a target foreground image and background area coordinate information based on the masks of the target foreground and the background; and integrating the target foreground image and the background area coordinate information by using an adaptive image fusion technology to generate a new target sparse scene image, and adding the newly generated target sparse scene image into the training data set of the target detection model. According to the method, only a small number of target objects and background images are needed, a large number of new high-quality images can be generated, the problem of scarcity of scene data is solved, and rich data resources are provided for subsequent model training.

The invention discloses an adaptive rendering method and system for characters and images in AI digital human virtual and real scene fusion, and the method comprises the following steps: S1, collecting Chinese text and image data, and extracting semantic and regional features; s2, constructing a Shenchang differential equation converter model, and inputting text and image features to generate fusion representation; s3, extracting an attention weight matrix, and determining the spatial arrangement position of the Chinese text in the image; s4, optimizing the structural parameter vector by adopting a luminous insect colony optimization algorithm to obtain a fusion model; s5, generating an image-text rendering instruction set based on the preliminary arrangement and optimization model; s6, in combination with the digital human action state and background image information, attitude mapping and illumination adjustment are completed to generate a rendering frame; and S7, inputting the rendering frame into a rendering engine, and outputting the video content fused by the Chinese characters and the images. According to the method, accurate fusion of Chinese semantics and images is realized, and the naturalness and interactivity of AI digital human image-text presentation are remarkably improved.

The embodiment of the invention provides an image processing method and device, a storage medium and computing equipment. Comprising the following steps: performing image segmentation processing on a target area in a source image to obtain a first mask image for the target area; performing superposition processing on the target area in the source image according to the first mask image to obtain a background image; wherein the background image comprises a source image after a first foreground image displayed in the target area is removed; inputting the background image and the first mask image into a pre-trained AIGC model to generate a target image; wherein the target image has the same background image, and a second foreground image replacing the first foreground image is displayed in the target area of the target image.

The embodiment of the invention provides a model training and defect detection method and device, equipment and a readable storage medium, relates to the technical field of image processing, ensures that defect image samples have enough quantity and high-quality labeling of the samples, and improves the performance of a deep learning model. The method comprises the steps that a sample data set is acquired, the sample data set comprises a plurality of composite images, and the composite images are obtained by performing first data enhancement on a foreground image and a background image; a first loss function and a second loss function are determined, the first loss function is used for representing the similarity loss between different synthetic images corresponding to the same foreground image, and the second loss function is used for representing the difference between the predicted value and the true value; the sample data set is input into a deep learning model, the deep learning model is trained according to the first loss function and the second loss function, the trained deep learning model is obtained, and the deep learning model is used for detecting the appearance defect condition of the equipment.

Synthesizing training data for training a change detection model includes receiving a patched image comprising a background image with a patch pasted into the background image. It further includes synthesizing a harmonized patched image at least in part by harmonizing the patched image using a machine learning model trained on the background image. It further includes providing as output a synthetic training sample usable to train a change detection model. The synthetic training sample includes a reference image, at least a portion of the harmonized patched image, and a corresponding mask.

The present disclosure relates to a method for generating a composite image, executed by one or more processors. The method for generating a composite image includes receiving a foreground image, receiving a background image, generating information on a position and size within the background image from the foreground image and the background image using a first artificial neural network, and generating a composite image based on the foreground image, the background image, and the information on the position and size within the background image.

To provide a food information providing device for encouraging customers to order and contributing to increase in an average customer spend in stores for providing food products such as conveyor belt sushi.SOLUTION: A food information providing device A as an example of the food information providing device, comprises a rail display part 1. Screens displayed on the rail display part 1 include a top screen 13, where the top screen 13 displays menu image data 130, menu name data 131, background image data 132, and character image data 133. Further, the plurality of menu image data 130 and menu name data 131 are displayed by scrolling in a fixed direction in set order. Furthermore, regarding the top screen 13, when the screen is touched with a finger and a right swipe operation or a left swipe operation is performed, the menu image data 130 having been displayed by the scrolling can be moved in a direction of the scrolling or in an opposite direction of the scrolling and displayed.SELECTED DRAWING: Figure 4

The invention provides an industrial defect image generation system and method based on deep learning, and relates to the technical field of artificial intelligence. A defect form adaptive module, a physical attribute modulation module and a multi-mechanism fusion module are integrated in a defect image generation module; dynamically selecting a feature extraction unit according to the defect type label based on a pre-constructed generative network model, and generating a defect feature map; generating an affine transformation parameter based on the physical attribute vector, and performing channel-by-channel linear modulation on a defect feature map of a middle layer of the generative network model, so that a multi-scale defect feature map finally generated by the generative network model contains specified defect type features and physical attribute features; and fusing the multi-scale defect feature image and the defect-free background image to obtain a fused defect image. The problems that in the prior art, industrial defect image generation is insufficient in sense of reality, poor in controllability and poor in fusion effect are solved, the method can be used for data enhancement of industrial visual inspection, and downstream model performance is improved.

The invention relates to the technical field of image processing, and provides an image rain removal method based on space-frequency double-domain perception, which comprises the following steps of: 1, constructing an image rain removal network based on space-frequency double-domain perception; 2, training the image rain removal network model in the step 1 until the model converges; and step 3, for any acquired rainy day scene image, reasoning by using the rain removal network trained in the step 2 to obtain a rain-free background image. Compared with the prior art, the rain-removed image generated by the method has fewer rain stripe residues and clearer texture features, and the problems of rain stripe residues, blurred background and the like in an existing image rain-removing method can be effectively solved.

The embodiment of the invention relates to the field of artificial intelligence, and discloses a workpiece machining quality detection method based on artificial intelligence. The method comprises the following steps: acquiring workpiece images of at least two angles of a current workpiece, determining a camera pose and image depth information, and establishing a three-dimensional voxel model of the current workpiece; acquiring attribute information of the current workpiece, distributing the attribute information to each voxel of the three-dimensional voxel model, and performing Gaussian sputtering on each voxel; determining a mask of each workpiece image in the workpiece image set, and dividing the workpiece images into workpiece structure images and background images according to the masks; the workpiece point cloud of the current workpiece is determined, the similarity between the workpiece point cloud and a preset workpiece standard point cloud is calculated, and if the similarity exceeds a preset similarity threshold value, it is determined that the current workpiece is a qualified workpiece. The problems of low efficiency and poor precision of manual workpiece detection can be at least solved. And a quantifiable quality standard is lacked, so that a detection result is difficult to accurately compare and analyze.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses an image generation method, device and equipment based on theme information and a medium. The method comprises the steps that input information is analyzed to generate theme information and copywriting information, a cue word set is generated, and a figure image set and a background image set are generated; fitting the segmented figure image with the background image to form a head image candidate set, and selecting a head image matching template frame to generate a basic image; decomposing the copywriting to generate a sub-module initial picture set, and adding a gradual change effect to form a sub-module picture set; the adjusted sub-module pictures are obtained based on size adjustment, and a pre-synthesized image is generated through splicing; and identifying the blank area to draw a title text to obtain a final image. Through theme analysis, template matching, image splicing, modular copywriting processing and blank drawing, poster generation efficiency is improved, layout flexibility is enhanced, and visual unification is realized.

The invention provides an adversarial digital camouflage generation method, device and equipment, and the method comprises the steps: carrying out the encoding of an obtained target background image based on an encoder, and forming a first hidden variable; performing denoising processing on the first hidden variable in a hidden space based on a denoising diffusion model to form a second hidden variable; processing the second hidden variable based on a decoder to generate a digital camouflage image; processing the first hidden variable based on an adversarial noise generator to generate an adversarial noise image; and obtaining an adversarial digital camouflage image corresponding to the target background image based on the combination of the camouflage image and the adversarial noise image. According to the adversarial digital camouflage generation method provided by the invention, the adversarial digital camouflage image can be quickly and accurately generated, so that the camouflage effect is good and the adversarial digital camouflage image is not easy to find when facing a neural network classification model.

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital designs utilizing a diffusion neural network to preserve readability and design composition while modifying image content background images and design assets. In some embodiments, the disclosed systems access a text prompt defining visual attributes of a digital design. Furthermore, the disclosed systems generate a modified text prompt by replacing chromatic information within the text prompt. Additionally, the disclosed systems determine an adaptive strength for a diffusion neural network from the text prompt. Also, the disclosed systems generate a modified digital design utilizing the diffusion neural network to process the modified text prompt according to the adaptive strength.

The invention discloses a rainfall field image extraction method based on double-domain collaboration and progressive feature decoupling. The method comprises the following steps: acquiring a rain image; respectively inputting the rain image into the rain layer branch and the background branch, carrying out corresponding image block embedding operation, and generating an initial rain layer feature and an initial background feature; performing feature extraction on the initial rain layer features through a learnable wavelet transform algorithm to obtain rain layer features, and performing feature extraction on the initial background features through frequency domain separation convolution to obtain background features; performing multi-scale progressive coupling feature extraction on the rain stripe features and the background features to obtain processed rain layer features and processed background features; and performing multi-scale up-sampling on the processed rain layer features and the processed background features to reconstruct a rain layer image and a rain-free background image, and performing weighted fusion on the rain layer image and the rain-free background image through learnable residual gating to obtain a reconstructed rain image and a rainfall field image. According to the invention, accurate separation of the rainfall field can be realized.

A unified virtual background image is generated for multiple participants of a video conference to create an immersive conference experience based on its use within video streams of those multiple participants. Generative artificial intelligence software associated with a conferencing system obtains input associated with a video conference. The generative artificial intelligence software generates a virtual background image based on the input. The virtual background image is then for use within multiple participant video streams during the video conference

The invention relates to the technical field of information processing, in particular to an anomaly detection method and device based on low-rank embedding and multiple scales and electronic equipment. The method comprises the following steps: acquiring a hyperspectral image, and preprocessing the hyperspectral image to obtain an original hyperspectral image; performing feature extraction operation on the original hyperspectral image by using a preset low-rank background feature extraction model to obtain low-rank background features, and extracting global features and local features of the original hyperspectral image by using a pre-constructed multi-scale fusion feature extraction model; and carrying out integration processing on the low-rank background features, the global features and the local features, comparing the obtained target reconstruction background image with the hyperspectral image, and identifying an abnormal region. Therefore, hyperspectral image disaster monitoring is realized by adopting low-rank background feature extraction and multi-scale fusion feature extraction, the problems of long time consumption, low efficiency and low precision in the detection process of the existing detection method are solved, and the method has the advantages of automation, high precision, rapidness, high efficiency and the like.

Systems and methods are provided for image editing, and more particularly, for harmonizing background images with text. Embodiments of the present disclosure obtain an image including text and a region overlapping the text. In some aspects, the text includes a first color. Embodiments then select a second color that contrasts with the first color, and generate a modified image including the text and a modified region using a machine learning model that takes the image and the second color as input. The modified image is generated conditionally, so as to include the second color in a region corresponding to the text.

The invention provides a dynamic target identification method and device for a remote sensing image, equipment and a medium, and belongs to the field of image processing. Extracting a plurality of candidate areas from the target remote sensing image through RPN; determining the candidate region with the dynamic target as a target region; determining a foreground image through the maximum between-cluster variance of the target area, and extracting an image of a dynamic target in the foreground image; and introducing a dense prediction module DPM into the CNN to construct a convolutional dense prediction network CDN, and inputting the image of the dynamic target into a dynamic target recognition model to obtain a recognition result. The method comprises the following steps: firstly, extracting a candidate region to reduce the information amount needing to be processed by a subsequent model, thereby facilitating the improvement of the detection accuracy, secondly, extracting an image of a dynamic target, further reducing the influence factors of a background image, finally, inputting the extracted target image into a CDN, and carrying out the feature enhancement and re-recognition of the image through the CDN, thereby improving the detection accuracy. And the accuracy of dynamic target identification is improved again.

Methods, systems, and non-transitory computer readable storage media are disclosed for generating digital images with a diffusion-based generative neural network conditioned on background-extracted lighting features. The disclosed system determines, in response to a request to generate a digital image, a target background image for inserting a foreground object into the target background image. The disclosed system generates, from the target background image and utilizing a lighting conditioning neural network, a lighting feature representation indicating one or more lighting parameters of the target background image. Additionally, the disclosed system generates, utilizing a diffusion-based generative neural network conditioned on the lighting feature representation, the digital image including the foreground object inserted into the target background image based on a composite image comprising the foreground object and the target background image with a foreground mask corresponding to the foreground object.

The invention discloses a behavior recognition method, device, server and system for multi-person tracking, and the method comprises the steps: obtaining a video sequence, and carrying out the foreground and background segmentation of the video sequence; performing fuzzy processing on the background image, fusing the background image with the foreground image to obtain a target image, and executing the following tracking steps: extracting a current video frame to be processed from the target image, and identifying each moving target in the current video frame; calculating the intersection-to-union ratio between the detection track of each moving object in the current video frame and the prediction tracks of all moving objects in the current video frame, and constructing a cost matrix according to the intersection-to-union ratio; optimizing the cost matrix, finding out a matching scheme with the minimum total cost, optimizing the matching of each moving target based on the matching scheme, updating the trajectory of the moving target, and repeatedly executing the tracking step until the tracking result of each moving target in the whole video sequence is obtained. And identifying the abnormal behavior of the moving target according to the tracking result.

The invention belongs to the technical field of image processing, and discloses a maskless image synthesis method and system based on a diffusion model, and the method comprises the steps: inputting a background image and a noise image containing a target object into a pre-trained potential diffusion model, and enabling the potential diffusion model to execute a reverse denoising process under the guidance of a condition vector, the target object is synthesized in a self-adaptive mode, and a synthesized image is obtained; wherein the condition vector acquisition mode comprises the following steps: encoding a reference image containing a target object into an object embedding vector, and generating a group of learnable background cue words according to the object embedding vector; splicing with the background prompt word; and performing spatial mapping on the spliced feature representation to obtain a condition vector. The method can overcome the defects that in an existing image synthesis technology, the process is tedious, the efficiency is low, a large amount of manual intervention is needed, the synthesis result lacks the sense of reality and harmony, and especially the foreground object cannot be adaptively adjusted according to the background environment.

A method for training an image generation model, a method for generating a digital human image, and related apparatuses are provided, relating to the fields of artificial intelligence, big model, big data and other technologies. The method for training an image generation model includes: obtaining N target facial images of a target face, wherein N is an integer greater than 1; inputting the N target facial images and at least one target background image into a preset image generation model to obtain a target digital human image after the target face is fused with each target background image; and training the preset image generation model based on a degree of difference between a first facial feature in the target digital human image and a second facial feature of the target face in the target facial images to obtain a target image generation model.

The invention discloses an irregular small target identification method under a non-high-definition complex background image. A multi-scale feature pyramid is constructed through bidirectional feature fusion, so that the feature expression ability of a small target is enhanced; applying a space-channel attention module to adaptively highlight target features and suppress complex background interference; by introducing a composite loss function including class balance focus loss and enhanced bounding box regression loss, model training is optimized to deal with class imbalance and improve the positioning precision of an irregular target. A self-adaptive multi-scale detection head is adopted, and dynamic feature fusion and scale perception branches are utilized to realize accurate detection of targets with different sizes; according to the method, the problems of low recognition precision and poor adaptability caused by weak features, background interference and irregular shapes of irregular small targets in low-resolution and complex background images are effectively solved, and the monitoring performance in actual applications such as unmanned aerial vehicle aerial photography and remote monitoring is remarkably improved.