470 results about "Model image" patented technology

The invention discloses a generation method and system for controllable high-quality AI drawing picture description, and the method comprises the steps: carrying out the analysis and recognition of the drawing intention of a user through a natural language processing technology, and extracting key drawing elements from the drawing intention; the meanings of the elements and the relation between the elements are understood on the basis of a deep learning neural network model, and the drawing intention of the user is expanded and supplemented on the basis of a generative adversarial network, so that various drawing cue words in different directions are generated; and on the basis of the drawing cue word, generating an image according with the description of the drawing cue word by utilizing a diffusion model image generation algorithm, and obtaining various styles of images according with an expected quality standard by introducing an image quality evaluation system. The method has the advantages that user thinking divergence can be guided, creativity is stimulated, effective interaction is achieved, feedback optimization results are fully utilized, image quality is greatly improved, and generation diversity and flexibility are increased to adapt to various requirements and scenes.

The invention discloses a modal language model image editing technology fusing non-perpetual culture elements. The modal language model image editing technology comprises the steps that a model is selected and trained, an LLaMA model is selected as a basis, LoRA is introduced for adaptive fine adjustment, and in this way, the model is subjected to adaptive adjustment under the condition that original parameter freezing is kept; according to the method, the understanding and reasoning capabilities in instruction editing are enhanced by combining MLLM (such as LLaVA), the MLLM can perform collaborative learning across text and image modalities and extract deep semantic information, so that the model can not only process basic instructions, but also understand complex non-perpetual culture elements, and the method has great significance in improving the understanding of the model on the non-perpetual culture elements. An enhanced bidirectional interaction mechanism is designed, and the mechanism realizes deep interaction between image and text features through a cross attention mechanism, so that the image features can be used as query and key value pairs to perform bidirectional communication with the text features, and the expression of a model in a complex non-perpetual scene is improved.

The invention discloses a diffusion model image generation method and device for structural disturbance guidance and consistent distillation fusion, and the method comprises the steps: carrying out the initialization of a first student network through a diffusion model, and initializing a first teacher network; generating an initial state of the submerged space according to the submerged space data set and a noise scheduling function of the diffusion model; introducing the classifier-free guidance after the structural disturbance into a first teacher network to obtain a second teacher network; according to the first teacher network, the second teacher network and the initial state of the submerged space, state prediction is carried out through a solver, and enhanced input of the first teacher network is generated; obtaining consistency loss according to the first student network, the first teacher network and the enhanced input; according to the consistency loss, performing parameter updating on the first student network to obtain a target model; the target model is used for generating a target image. The method can improve the quality of the generated image and increase the generation speed of the diffusion model, and can be widely applied to the technical field of image generation.

The invention discloses a blind area prompting method and device, electronic equipment and a storage medium, and belongs to the technical field of vehicle application, and the method comprises the steps: determining a target blind area of a target vehicle according to a to-be-driven route of the target vehicle; acquiring a first environment image shot by an environment camera corresponding to the target blind area; performing target detection based on the first environment image, and generating first state information of each traffic participant in the target blind area; and based on the first state information of the traffic participant, generating an environment modeling image containing the traffic participant and displaying the environment modeling image. The target vehicle can notice traffic participants in the blind area in time, the driving safety of the target vehicle can be improved, target detection is carried out on the target blind area determined by the to-be-driven route of the target vehicle, the target vehicle can be prevented from processing images of all environment cameras in the current environment, and the driving safety of the target vehicle is improved. The data volume needing to be processed in the blind area detection process is reduced, and the blind area reminding efficiency and speed of the target vehicle can be improved.

The invention provides a visual vehicle control method and device based on a vehicle model and a storage medium. The method comprises the following steps: generating a vehicle model image of a vehicle model according to a controllable function list; cutting a controllable component in the car model image, and determining coordinate information of the controllable component; drawing the car model image and the controllable component on the interface of the client according to the interface size of the client and the coordinate information of the controllable component; binding the vehicle control state of the controllable component with the picture processing logic; in response to an interactive operation of a user on the vehicle model image, converting parameters collected by the interactive operation into a vehicle control instruction; and a vehicle control instruction is sent to the vehicle, the loading dynamic effect is displayed in the controllable component area in the vehicle model image interacted by the user, a control result returned by the vehicle is received, and the display state of the controllable component in the vehicle model image is updated according to the control result. The vehicle control operation is more visual and comprehensive, the operation is easy, and the user experience and the operation efficiency are improved.

The invention discloses a foggy day perception-based feature refinement ship instance segmentation method and equipment, and belongs to the field of instance segmentation of ship images in a foggy day scene. According to the method, YOLOv8s is used as a basic model, a joint learning framework is designed, and defogging and feature refinement enhanced perception strategies are combined. Through a state space model and a multi-scale channel aggregation gating strategy, modeling image features are refined, and foggy day long-distance dependence feature information captured by the model is enhanced. And through the adaptive defogging module, fog background interference features are reduced. Through multi-window branch feature extraction and a multi-angle similarity measurement strategy, the ability of the model to extract local detail information and global information is further enhanced, the focusing ability of a ship target area and the adaptability to a complex haze scene are improved, and the ship instance segmentation performance and generalization ability in a foggy day scene are effectively improved.

The invention discloses a digital twin terrain rapid construction method based on oblique photography, and relates to the technical field of geographic model image processing, and the method comprises the steps: data collection based on oblique photography: employing an oblique photography mode to collect bidirectional terrain image data at two sides of a path in a cross manner; image processing: performing preprocessing, feature extraction and classification on the terrain image data acquired in the two directions to generate training data; model training: constructing and training a deep learning model, and identifying and classifying topographic features in the bidirectional topographic image data; digital twinborn modeling: constructing a digital elevation model and a digital surface model, and obtaining digital three-dimensional terrains on the two sides of the flight path; and result verification: combining the digital three-dimensional terrains on the two sides of the path, and verifying with an actual site. According to the method, the deep learning model is constructed and trained, and digital twin modeling is performed according to the training result, so that the construction speed and precision of the terrain model can be greatly improved.

A virtual try-on method and apparatus, and a storage medium. The method comprises: acquiring a clothing image to be subjected to try-on and a first model image; on the basis of the clothing image to be subjected to try-on, determining a target clothing image; on the basis of the first model image, determining a try-on area image and a first key point, wherein a try-on area comprises an area of model clothing, a body area which is in contact with the model clothing, and a background area which is in contact with the model clothing; and on the basis of the target clothing image, the try-on area image and the first key point, generating a try-on effect image by means of a trained diffusion model.

The invention discloses an overhead transmission line mechanical construction three-map one-table intelligent generation method, which comprises the following steps of: fusing a digital orthoimage model, elevation data and a power transmission and transformation project model through a coordinate transformation matrix, and establishing a three-dimensional scene with a terrain curvature attribute; based on the terrain curvature and equipment coordinates of the three-dimensional scene, a multi-objective optimization algorithm is adopted to synchronously plan a composite path of a cableway, a track and a road, and a road network list map containing an obstacle avoidance topology is generated; recognizing a tower footing projection polygon in the three-dimensional scene, segmenting the types of surface attachments in combination with a digital orthoimage model image, and generating a surface feature list map with a water and soil conservation identifier; and establishing a mapping function of the terrain curvature and the environment water conservation rule, outputting equipment types and spatial poses according to the hoisting safety margin and the earth surface disturbance threshold value, and generating an equipment list map. According to the method, a unified space reference and multi-system dynamic cooperation mechanism is constructed, and the planning precision and construction compliance of three graphs and one table are remarkably improved.

The invention provides a method and a system for processing a cell image based on a DistSegNet model. The method for detecting the cells based on the DistSegNet model image processing technology comprises the following steps: preprocessing a collected cell image; performing cell segmentation on the cell image based on a DistSegNet model image processing technology to generate a cell nucleus region; based on the segmented cell nucleus region, generating a background region, a foreground region and an edge region by adopting morphological operation; calculating the shortest Euclidean distance from each background region pixel to the nearest foreground region pixel, and segmenting the cell image by using a watershed algorithm; performing result optimization on the segmentation map corresponding to each cell instance label to obtain a filtered segmentation label map; and extracting the outer contour of the intra-nucleus region and the outer contour of the surrounding region of each cell from the segmentation mark graph, and storing the outer contours to a corresponding result file. According to the invention, the accuracy and accuracy of a WSI-level cell detection result can be improved.

Methods and systems are disclosed for enhancing or modifying an image by a diffusion model. The methods and systems receive a first image depicting a real-world scene including a target object and receive input associated with adjusting a zoom level of the first image. The methods and systems, in response to receiving the input, modify the zoom level associated with the first image to generate a second image having a view of the target object that is different from a view of the target object in the first image. The methods and systems analyze the second image using a generative machine learning model to generate an artificial image that modifies portions of the second image to improve the view of the target object relative to the second image.

The invention relates to a lightweight multi-modal image fusion method based on a knowledge distillation technology. Compared with the prior art, the lightweight multi-modal image fusion method based on the knowledge distillation technology overcomes the defects that an image fusion method based on text guidance is large in calculation overhead and large in model scale. The method comprises the following steps: obtaining and preprocessing a source image; constructing a lightweight image fusion model; training a lightweight image fusion model; obtaining a to-be-fused image; and obtaining a multi-model image fusion result. According to the method, through a teacher-student network architecture and a customized prior distillation process, the semantic understanding ability of a large language model is successfully transferred to a lightweight student network, and under the condition that text guidance in a reasoning stage is not needed, relatively high fusion quality is still kept, and meanwhile, the calculation overhead is remarkably reduced.

A method of a clothing virtual try-on service based on deep learning allowing a virtual try-on service application executed by at least one processor of a computing device to perform a process of the clothing virtual try-on service based on the deep-learning includes: determining a first clothes image including a first clothes object, a second clothes image including a second clothes object, and a model image including a model object; generating a first transformed clothes image by transforming a shape of the first clothes object to correspond to the model object; generating a second transformed clothes image by transforming a shape of the second clothes object to correspond to the model object; and generating and outputting a virtual fitting image obtained by synthesizing the first transformed clothes image and the second transformed clothes image to be virtually fitted on the model object.

The invention discloses an anti-corrosion control system and method for a pipeline operation robot, and relates to the technical field of robot control, and the system is composed of a plurality of functional modules, and comprises a multi-sensor fusion module which obtains a pipeline image in real time through a camera; meanwhile, a sensor is used for dynamically collecting internal environment parameters of the pipeline; the three-dimensional modeling and positioning module is used for constructing a pipeline three-dimensional model based on an SLAM algorithm and the pipeline image and positioning the position of the pipeline where the robot is located in real time; the intelligent decision-making module is used for identifying a pipeline corrosion area and position by utilizing YOLOv5 based on the pipeline image and performing corrosion analysis on the corrosion area, and the corrosion analysis comprises corrosion thickness and form contour; measuring the corrosion thickness of the corrosion area by utilizing electromagnetic eddy current detection, and extracting the shape contour of the corrosion area by utilizing deep learning model image recognition; and triggering a self-adaptive control strategy according to the internal environment parameters of the pipeline and the pipeline position of the robot.

The invention discloses a multi-mode image fusion recognition method and system based on multi-task collaborative learning, and the method comprises the steps: inputting a multi-mode image into a pre-trained multi-mode image fusion recognition network, and carrying out the image recognition, so as to obtain a multi-mode image fusion recognition result, comprising the following steps: extracting a plurality of feature maps with different resolutions through an encoder; extracting a feature map of a corresponding mode through an image fusion network, extracting an image fusion weight, carrying out element multiplication operation on the image fusion weight and the original image of the corresponding mode, and then adding to generate a fused image; performing weight-guided feature fusion based on the image fusion weight through a weight-guided feature fusion module to obtain fusion features of different resolutions; and decoding through a semantic segmentation decoder to obtain a multimode image fusion recognition result. The invention aims to realize close combination of multi-modal image fusion and segmentation to improve respective performances, so as to realize accurate estimation of the position of the interested target and accurate identification of the category.

The invention provides a compressed sensing iterative reconstruction method combining image level features. Relates to the technical field of graphic image processing. The image reconstruction quality is gradually improved by alternately using a gradient descent operation and a feature optimization operation. In each iteration stage, firstly, a multi-scale feature enrichment module MFEM is constructed, denoising of different scales is carried out on a reconstructed image in the previous stage, and the reconstructed image is enhanced into a multi-channel feature map. And then updating fine-grained information of the feature map by adopting gradient descent operation. Secondly, in order to enhance the perception capability of the network for high-resolution images and reduce the calculation complexity, a secondary spatial information capture module SSCM is constructed, and image level features are modeled through a lightweight CNN-Transform hybrid architecture and are deeply optimized. And finally, non-linear enhancement is performed on the feature information optimized by the SSCM through a post-processing module PPM, and a reconstructed image of the stage is obtained. After multiple iterations, a final reconstructed image can be obtained.

The invention discloses a multi-modal remote sensing image fusion classification method under a modal missing condition, and the method comprises the steps: constructing a multi-modal remote sensing image model image fusion classification model, taking the data of three remote sensing image modals as input, carrying out the feature extraction of the data of each modal through a respective specific feature encoder and a shared feature encoder, and carrying out the feature extraction of the data of each modal; the method comprises the following steps: firstly, generating a specific feature, then fusing the specific feature and the shared feature, generating a single-mode fusion feature by adopting a jump link, and finally, fusing the fusion features of the three modes again, and generating a final fusion feature for model prediction. Two auxiliary tasks are introduced into the model, one is a domain classification task based on specific features, and the other is a comparative learning task for shared features. The model is not only suitable for full-modal training, but also effectively extracts and fuses the multi-modal features under the condition that partial modals are missing, and the classification performance of the model is improved.

The invention relates to the field of intelligent architecture diagram design rationality judgment, and discloses an architecture diagram rationality analysis and judgment method based on multi-modal feature fusion, and the method comprises the steps: obtaining a to-be-analyzed architecture diagram; identifying and extracting annotated text information in the architecture graph, and recording the annotated text information; identifying and acquiring a region-of-interest feature map set of the image elements through an R-CNN model, and recording the region-of-interest feature map set; establishing a position and logic information corresponding relation between OCR module text information and R-CNN model image elements, and generating an extended text description; performing word segmentation processing and semantic coding on the expanded architecture image text to obtain a word granularity feature vector set; performing semantic coding to obtain a word granularity feature vector set; generating comprehensive feature vectors of the same dimension; and calculating a semantic matching coefficient, and judging whether the design of the to-be-analyzed architecture graph meets the rationality requirement of overall planning or not. Whether the design and the function of the architecture diagram meet the overall planning requirement can be effectively evaluated, and the accuracy and the efficiency of analysis and review are improved.

Disclosed herein are methods, systems, and computer-readable media for generating image captions for training a machine learning model. Current image generation models are hindered by the prevalence of improper or inaccurate captions, which leads to suboptimal training data. This results in less effective image generation models. Disclosed systems and methods involve obtaining a text-to-image dataset including one or more digital image-caption pairs. Systems and methods involve generating a recaptioned dataset by applying an image captioner model to images in the text-to-image dataset. An image captioner model can be trained with an improved image dataset, a first tuning stage, and a second tuning stage, for improved performance.

The invention discloses a method for automatically generating an AI model, which belongs to the technical field of image generation and comprises the following steps: acquiring basic characteristics, posture information and clothing description of the AI model; a model image is generated through a diffusion converter according to the basic features, the clothing description and the posture information, the model image is optimized through an optimizer, and the optimized model image is obtained; wherein the diffusion converter is optimized by combining LoRA; carrying out background fusion and adjustment on the optimized model image to obtain a final model image of the AI model; according to the technical scheme, the high-quality customized AI model image can be efficiently generated.

The invention provides an intelligent bill recognition method based on a deep neural network model, and relates to the technical field of intelligent bill recognition based on the deep neural network model.The intelligent bill recognition method comprises the steps that various bill data are collected, image features and text features are extracted respectively and preprocessed, and complete multi-modal data support is provided for subsequent modeling; secondly, modeling image features by using a convolutional neural network and modeling text features by using a deep neural network, splicing the image features and the text features into a joint feature vector, and deeply fusing information of an image and a text modal through a cross-modal attention mechanism to enhance multi-modal relevance; and finally, designing a dynamic weight adjustment mechanism, adaptively adjusting the optimization weights of the cross entropy loss of the classification task and the mean square error loss of the field analysis task based on the cross entropy loss of the classification task and the mean square error loss of the field analysis task, and balancing optimization conflicts in a multi-task scene.

Provided in the present disclosure are a method and system for enhancing the sense of reality of a virtual model on the basis of a generative network. The method comprises: acquiring a rendered image of a virtual model wearing digital clothing; determining whether parsing information about the digital clothing in the rendered image is known; if the parsing information is unknown, performing extraction on the basis of a preset algorithm; converting the parsing information and then inputting converted parsing information into a generative network; under the control of a generative control condition, making the generative network generate a model character with a stronger sense of reality in a model area on the basis of model information; and converting the model character to obtain a generated image of a model wearing the digital clothing. By means of the solution in the present disclosure, on the basis of generative AI technology with high controllability, the sense of reality of clothing models can be significantly improved by fully utilizing priori information of digital clothing and priori information of a virtual model; and the high fidelity of modeled clothing is also kept, such that the solution is applied at a high adaptability to the alignment from the virtual model in a digital world to a real person model in a real world.

The present application relates to the field of drones, and in particular to a method, device and medium for measuring and three-dimensional modeling analysis of underground pipelines based on drones, including: obtaining initial pipeline information of underground pipelines, and determining the ultrasonic penetration frequency standard of underground pipelines based on the initial pipeline information; obtaining current ultrasonic information, and determining whether the ultrasonic information meets the ultrasonic penetration frequency standard; if it does, calculating the time difference information of sending and receiving the ultrasonic information, and determining the distance information between the drone and the underground pipeline according to the time difference information of sending and receiving; obtaining the current position information of the drone, combining the distance information and the position information to generate the three-dimensional model image information of the underground pipeline; and controlling the display of the three-dimensional model image information of the underground pipeline. The present application has the effect of improving the measurement efficiency of underground pipeline measurement.

In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

The invention discloses a self-adaptive image fog removal method guided by a large-scale multi-modal model, belongs to the technical field of visual information processing, and is applicable to the field of foggy day scene image processing. The implementation method of the invention comprises the following steps: 1, obtaining degradation prior by using a pre-trained large-scale multi-modal model; 2, inputting the fog image and the degradation priori into a MoE-SSM model for training, so as to dynamically adjust model parameters and further perform dynamic perception defogging; 3, fusing the shallow feature Fs and the optimized feature # imgabs0 #, and reconstructing a clean and fogless image; 4, training a neural network by using a clean and fogless image and a truth value clear image by using a Charbonier loss function shown in a formula (8), so as to punish the deviation between the recovered image and the truth value clear image and encourage a consistent image gradient; compared with the prior art, the problem of compromise processing of receptive fields and calculation efficiency in existing defogging model image processing is solved, meanwhile, the requirement for a large amount of annotation data is reduced, and then the image processing accuracy and stability are improved.

The invention discloses an image processing method and device, a medium, electronic equipment and a program product. The method comprises the following steps: acquiring an article image comprising a first article and a model image comprising an interaction posture of a model and a second article; superposing the article image to the position of the first limb in the model image to replace the second article in the model image with the first article to obtain a first image; obtaining a first mask picture of the foreground area including the first article and the first limb; and according to the first mask image, performing local redrawing on the first limb in the first image to obtain a second image. Through superposition of the article image and the model image, the first article and the model are fused, and the real consistency of the generated content can be ensured. And according to the first mask image, local redrawing is carried out on the shielding conflict area in the first image, so that the natural interaction feeling of the model and the first article is improved.

The invention relates to the technical field of industrial detection, and provides a real-time monitoring method and device for slag in a boiler. A plurality of high-temperature-resistant cameras are installed around an observation opening in the bottom of a boiler in an annular array mode, the slag accumulation condition in the boiler is collected in real time through the high-temperature-resistant cameras, and a single-view-angle image is obtained; evaluating the visual field states of the high-temperature-resistant cameras according to the single-visual-angle images, and determining a plurality of to-be-modeled images from the plurality of high-temperature-resistant cameras; and generating slag point cloud data by using the at least one to-be-modeled image, and performing three-dimensional reconstruction on the slag point cloud data to obtain the slag pile volume. According to the method, the slag falling condition of the boiler bottom of the power plant boiler is monitored and recognized in real time, and the problems that the slag falling at the boiler bottom cannot be detected in real time depending on manpower, the detection accuracy is insufficient, the three-dimensional form of the slag falling at the boiler bottom cannot be synthesized by detecting the slag falling at the boiler bottom through sensor equipment, and practicability is poor are solved.

The invention relates to the technical field of image processing and machine learning, provides a method for improving the image generation quality of a multitask visual basis model based on a diffusion model, and provides a multitask visual basis model image generation method based on the diffusion model. Comprising a visual low-level semantic information learning adapter expanded according to the number of tasks and a multi-task visual basic model with a feedback auxiliary learning mechanism, and the visual low-level semantic information learning adapter expanded according to the number of tasks comprises a group of parallel small-weight convolutional layer modules specific to different tasks. A convolutional layer module shared among different tasks is connected in series behind the convolutional layer modules of the specific tasks; and the feedback auxiliary learning mechanism guides the multi-task visual basic model to better train through the minimum feedback loss so as to promote the improvement of the final image generation quality. The method is mainly applied to image processing occasions.

The invention relates to the technical field of computer vision and artificial intelligence, in particular to a visual state space model-based neural network optimization method for bridge diseases, which comprises the following steps of: constructing a neural network comprising a feature extraction backbone network and a task adaptation head network, modeling an image feature sequence by the backbone network based on a visual state space model, the task adaptive header network is used for capturing local details and long-distance global dependence and outputting disease categories, confidence coefficients and positions; a standardized data set is used for training a model, and dynamic optimization is completed by evaluating the importance of neurons and sorting and cutting redundant neurons; and preprocessing a to-be-detected image, inputting the preprocessed to-be-detected image into the optimization model, and outputting a precise disease identification result through feature extraction, multi-branch processing and non-maximum suppression. The method improves the disease feature extraction precision, achieves the light weight of the model, adapts to multi-scale disease detection, improves the practicability of an identification result, and is suitable for a bridge disease intelligent detection scene.

The invention provides a method and a system for processing a cell image based on a DistSeg model. The method for detecting the cells based on the DistSeg model image processing technology comprises the following steps: preprocessing a collected cell image; segmenting the cell image based on a DistSeg model image processing technology to generate a cell nucleus region; based on the segmented cell nucleus region, generating a background region, a foreground region and an edge region by adopting morphological operation; calculating the shortest Euclidean distance from each background region pixel to the nearest foreground region pixel, and segmenting the cell image by using a watershed algorithm; performing result optimization on the segmentation map corresponding to each cell instance label to obtain a filtered segmentation label map; and extracting the outer contour of the intra-nucleus region and the outer contour of the surrounding region of each cell from the segmentation mark graph, and storing the outer contours to a corresponding result file. According to the invention, the accuracy and accuracy of a WSI-level cell detection result can be improved.