2763 results about "Human-body model" patented technology

The invention belongs to the technical field of knowledge visualization, and discloses a traditional Chinese medicine acupuncture knowledge visual display system based on a knowledge graph. Comprising the steps that a traditional Chinese medicine ancient book data acquisition unit, a clinical case data acquisition unit and an ultrasonic image data acquisition unit acquire data and integrate the data into traditional Chinese medicine acupuncture data, and the traditional Chinese medicine acupuncture data is preprocessed to obtain perfect traditional Chinese medicine acupuncture data; constructing a knowledge graph based on the perfect traditional Chinese medicine acupuncture data; constructing an optimization network model to optimize the knowledge graph to obtain a high-quality knowledge graph; constructing an incremental learning framework, updating the high-quality knowledge graph based on the incremental learning framework, and outputting a real-time updated knowledge graph; constructing an interactive three-dimensional human body model based on the real-time updated knowledge graph; based on the real-time updated knowledge graph and the interactive three-dimensional human body model, outputting an executable medical strategy for the application case, and sending the executable medical strategy to the student terminal; and the teaching quality is improved while knowledge visualization is realized.

The invention relates to the technical field of clothing data processing, in particular to a digital design method of three-dimensional prototype clothing. The method comprises the following steps: obtaining human body three-dimensional scanning data and carrying out feature point labeling, reconstructing a three-dimensional human body model as basic data of costume design, carrying out contour looseness calculation on the human body model, generating a looseness data set, carrying out sample plate plane analysis to obtain a plane sample plate data set, and after collecting costume fabric data, carrying out data processing on the plane sample plate data set. The method comprises the following steps: performing physical characteristic mapping on a human body model and a planar template, reconstructing a three-dimensional garment model conforming to fabric characteristics, performing spatial positioning on the template, performing virtual sewing simulation, generating a shape data set of the garment, performing dynamic motion analysis on the shape data of the garment according to the human body three-dimensional model, and evaluating the comfort level of the garment. The garment form is locally adjusted to reconstruct a planar template. According to the invention, a more comprehensive and more reliable digital design method of the three-dimensional prototype clothing is realized.

The invention relates to the technical field of vehicle safety, in particular to a pedestrian body model chest injury risk curve adjusting method. Comprising the following steps: analyzing the relationship between the speed and the chest injury risk, and drawing a first curve between the vehicle speed and the injury risk based on accident statistical data; fitting data of a rib cortical bone uniaxial stretching material mechanics experiment; constructing a vehicle-pedestrian side impact simulation experiment matrix under different working conditions, and generating a simulation sample number; extracting the rib strain of the human body model in the sampling model, calculating the fracture probability of a single rib of the chest of the human body model, and then calculating the maximum simple injury probability of the specified chest of the human body model; fitting the relationship between the vehicle speed in the simulation model and the chest injury risk of the human body model, and drawing a second curve between the vehicle speed in the sample and the chest injury risk of the pedestrian model; and constructing an objective function according to the difference between the first risk curve and the second risk curve. According to the technical scheme, the accuracy of accident damage prediction can be improved.

The invention provides a human body action recognition method based on machine learning, and solves the problem of action recognition in fitness training. According to the method, a Mediape framework is used for processing a video, key points of a human body are recognized, and a human body model is constructed; matrix perspective transformation is used for correcting video distortion, and the accuracy of the human body model is ensured; and the human body key points extracted by the Mediape are used as feature pairs to classify actions by using an SVM (Support Vector Machine). In addition, different training objects are distinguished by means of a YOLO-v7 model so as to adapt to the scene that multiple persons exercise at the same time. The high accuracy and performance of the method in action classification prove the potential of the method as a real-time feedback and guidance tool in fitness training. By accurately identifying and evaluating the athletic action, an individual can be helped to improve the athletic form and prevent athletic injury. The accurate motion recognition technology provides better fitness guidance and quality control for individuals.

The invention discloses a virtual fitting method and device, a storage medium and electronic equipment, and is applied to the technical field of computer image processing, and the method comprises the steps: processing a target video, and obtaining the human body posture data of each video frame in the target video; constructing a 3D human body model of each video frame by using the human body posture data of each video frame; for the 3D human body model of each video frame, acquiring clothing rendering information of the 3D human body model, and rendering virtual clothing on the 3D human body model based on a dynamic fitting algorithm and the clothing rendering information to obtain a virtual rendering video frame of the video frame; and generating an AR fitting video based on each virtual rendering video frame, and displaying the AR fitting video to the user. Therefore, the selected costume can be tried on in the AR form, the fitting effect of the costume can be displayed for the user, the problem that the size is improper due to the fact that the costume purchased online cannot be tried on is solved, the probability of refunding and changing goods is reduced, and good shopping experience is provided for the user.

The invention relates to a visualization method of an electronic medical record system and a visual medical record system. The method comprises the following steps: constructing a system main page; providing entry options, basic information corresponding to the patient, chief complaint information and current medical history information in the navigation bar area; loading and displaying the three-dimensional human body model in the three-dimensional human body model display area; in response to analysis of the electronic medical record information of the patient, automatically identifying and extracting lesion part information described in the medical record information; performing visual labeling on the mapped diseased region on the three-dimensional human body model; setting human body system options in the three-dimensional human body model display area; and in response to the operation that the mouse of the user hovers on the lesion part label on the three-dimensional human body model, displaying an examination result and abnormal index information related to the lesion part. According to the invention, the defects of an existing electronic medical record system in the aspects of information acquisition efficiency, spatial information presentation and information interaction modes can be effectively overcome, and the readability of medical record information and the diagnosis and treatment efficiency of doctors are remarkably improved.

Disclosed herein are systems, methods and instrumentalities associated with multi-view 3D human model estimation using machine learning (ML) based techniques. These techniques may use synthetically generated data to train an ML model that may be used to progressively regress a 3D human body model based on multi-view 2D images. The training data may be synthetically generated based on statistical distributions of human poses and human body shapes, as well as a statistical distribution of camera viewpoints. The progressive regression may be performed based on consensus features shared by the multi-view images and diversity features derived from at least one of the multi-view images. Consistency between the multi-view images may also be maintained during the regression process.

The invention provides a virtual fitting method based on a color three-dimensional model, and the method comprises the steps: obtaining the body point cloud data of a user through a three-dimensional scanning device, constructing a color three-dimensional human body model, and setting skeleton binding parameters; dividing a pressure sensitive area based on model surface curvature distribution, and generating a dynamic pressure map; performing cloth physical simulation on the model in a physical engine, and extracting deformation response data of the top points of the clothing grids; real-time motion posture data of a user is collected through an inertial sensor, motion distortion correction is conducted, and a joint motion track is generated. Dynamically comparing the joint movement track with the deformation response data to generate a clothing fitting degree deviation report; and optimizing the clothing pattern parameters and the fabric physical attributes based on the deviation report, and outputting a clothing adaptation proposal. According to the invention, the suitability and comfort of clothes can be improved, and the production efficiency and the product quality are improved.

The invention discloses a single-view three-dimensional dressed human body reconstruction method based on pixel and voxel feature fusion. The method comprises the steps of data set preprocessing, data set dividing, three-dimensional dressed human body reconstruction network construction, three-dimensional dressed human body reconstruction network training, three-dimensional dressed human body reconstruction network testing and reconstruction result displaying. In the pixel feature extraction network, the coordinate attention and the stacking hourglass network are combined, so that the pixel feature extraction precision is improved; in the voxel feature extraction network, a three-dimensional channel and space attention are introduced into the voxelization human body parameterization model network, and a multi-scale residual feature extraction module is combined to extract voxel features. And splicing the extracted pixels and voxel feature vectors, inputting the spliced pixels and voxel feature vectors into a multi-layer perceptron, and reconstructing a three-dimensional dressed human body model through Marking Cubes, thereby solving the technical problem of insufficient precision of the existing single-view three-dimensional dressed human body reconstruction method, and being applicable to the technical fields of artificial intelligence and computer vision.

Extraction of human poses from video data for animation of computer models. In some implementations, a computer-implemented method includes determining a first pose sequence of a human body model based on frames of an input video, the frames depicting movement of a person. The first pose sequence includes poses of the human body model that correspond to the video frames. The first pose sequence is updated to produce a second pose sequence, including, over multiple iterations, determining joint velocities of joints of the pose sequence, determining, in parallel, predicted poses from each of multiple poses of the pose sequence by encoding the joint velocities into parameters of a human motion prior, and based on comparing corresponding predicted poses, adjusting joint angles of the pose sequence. The second pose sequence can provide an animation of a computer model corresponding to the movement of the person in the input video.

The invention belongs to the technical field of three-dimensional reconstruction, and discloses a three-dimensional digital human generation method and system capable of voice interaction. According to the invention, brand new speaking audios in different languages are automatically generated according to different languages of the input target text and the sampled human voice audios; the sequential stability and detail reduction capability of three-dimensional human motion are guaranteed by using multi-model joint estimation and a sequential loss function, and facial expression details and hand postures in the image can be accurately estimated. After the high-precision three-dimensional human body model is obtained through estimation, human body action and expression generation is carried out based on voice driving, accurate synchronization of actions and expressions generated through voice is achieved, and facial expression movement and body posture movement, namely a whole-body three-dimensional human body model, conforming to brand-new speaking audio are accurately generated; and finally, rendering the whole-body three-dimensional human body model into a real digital human capable of voice interaction by using a three-dimensional neural rendering model. According to the invention, the realization of single person picture input, high-precision three-dimensional digital person generation and voice interaction is facilitated.

The invention relates to the technical field related to artificial intelligence, in particular to an intelligent medical diagnosis engine based on an AI large model, which comprises an auxiliary diagnosis module for collecting data such as an electronic medical record and a medical image of a patient and predicting an auxiliary result by using an integrated learning method; the drug recommendation module is used for analyzing drug recommendation data by using an AI large model and predicting potential curative effects and side effects of new drugs; and the operation simulation module is used for constructing an operation environment and a human body model in combination with a virtual reality technology. A large amount of medical data can be quickly processed and analyzed through auxiliary diagnosis, the diagnosis time is shortened, gene, physiological and pathological multi-omics data of a patient can be integrated by reducing unnecessary invasive examination and misdiagnosis and drug recommendation, a personalized drug treatment scheme is provided for the patient, and the patient experience is improved. Comprehensive and accurate diagnosis basis and treatment suggestions are provided for doctors; by accurately simulating a real operation scene including mechanical and optical characteristics, a more real training experience is provided for doctors and medical students.

The invention discloses a man-machine cooperation digital twinning simulation method based on virtual reality interaction, and relates to the technical field of man-machine collaboration.The method comprises the steps that a digital twinning three-dimensional scene, a digital twinning human body model and a digital twinning mechanical arm model are constructed, after human body posture data of a real tester and joint movement data of a real mechanical arm are obtained, a digital twin human body model is driven to move based on the human body posture data, a digital twin mechanical arm model is driven to move based on the joint movement data, virtual man-machine cooperation is achieved, and in the virtual man-machine cooperation process, the human body posture data of the real tester and the joint movement data of the real mechanical arm are obtained. And recording a human body collision part and a scene collision area in real time when the collision occurs, and subsequently testing and optimizing the collision prediction model. According to the method, a highly-simulated and immersive digital twin system is constructed, a real working scene can be safely and reliably reproduced, man-machine cooperation behaviors can be optimized, and the collision prediction model can be repeatedly tested and optimized under the condition that no real collision risk exists.

The invention discloses a single-view human body three-dimensional reconstruction method based on Gaussian surface elements, and the method comprises the steps: collecting image data from a plurality of human body data sets, carrying out the preprocessing through employing a targeted preprocessing strategy according to the data characteristics corresponding to each image data, and obtaining a processed human body data set; constructing a human body 3D Gaussian attribute prediction model, wherein the human body 3D Gaussian attribute prediction model comprises a hierarchical feature extraction module, a feature fusion network and a 3D Gaussian function decoder; training the human body 3D Gaussian attribute prediction model based on the processed human body data set to obtain a trained human body 3D Gaussian attribute prediction model; and performing three-dimensional reconstruction on an input human body picture based on the trained human body 3D Gaussian attribute prediction model, and outputting a reconstructed human body three-dimensional image. According to the method, the manufacturing cost of the virtual digital human is greatly reduced, and the efficiency and accuracy of constructing the dynamic human body model are improved.

In an embodiment, a method for human motion generation with open vocabulary scene-and-text context is provided. The method involves receiving an input that includes a 3D point cloud of a scene containing a goal object with a natural language instruction related to the goal object. A text tokenizer is applied to the text to obtain tokenized text, and a text encoder from a pre-trained vision-language model generates text features. First scene features are generated by applying a pre-trained U-Net scene encoder to the 3D point cloud, which are down sampled to obtain second scene features. A conditional latent is obtained by fusing the second scene features with the text features. A conditional motion generator predicts motion parameters for a parametric human body model over a specific time duration. Finally, 3D human meshes for multiple motion frames are obtained based on the motion parameters and the parametric human body model.

The invention discloses an intelligent scene type CPR visual training system based on an MR technology, which belongs to the technical field of non-special measurement for specific variables and comprises a training request sensing module, an intelligent scene automatic generation module, a sensing data acquisition module, a visual display and voice prompt module and a network performance evaluation management and control module. According to the method, the performance parameters of the sensing source nodes built in the simulation human body model are acquired and analyzed in real time, so that the data feedback precision in the training process is improved, and the data feedback precision in the training process is further improved; the problem of poor CPR visual training experience caused by lack of real-time performance monitoring and feedback mechanisms in the prior art is effectively solved.

The invention belongs to the technical field of deep learning, and particularly relates to a multi-modal gait recognition method based on SMPL modal decomposition and embedding fusion, and the method comprises the following steps: constructing a multi-modal gait recognition model DFGait fusing an SMPL model and a contour; providing an adaptive frame joint attention module, and adaptively extracting important joint information of a gait sequence key frame in an SMPL posture branch; a modal embedding fusion module is provided, and efficient fusion of two kinds of modal information is achieved by aligning and fusing SMPL model features and contour features in a unified semantic space; and jointly supervising the training of the DFGait model by using a joint loss function combining triple loss, cross entropy loss and modal consistency loss. According to the method, the SMPL human body model is decomposed, and gait information of dynamic postures and static shapes contained in the SMPL model is fully extracted. Branch optimization is carried out through an adaptive frame joint attention module, and finer spatial-temporal feature extraction of gait information is realized.

The invention relates to an editable human body reconstruction method and system based on three-dimensional Gaussian splashing, and the method converts a dynamic human body reconstruction problem into a reconstruction problem of a static template human body in a standard space, achieves the respective decoupling of the shape and the appearance through a mode of constructing the mapping of a three-dimensional Gaussian model and a parameterized human body model, and achieves the reconstruction of the human body. Human body reconstruction in an editable form is achieved, and the editable form comprises the steps that geometric editing is achieved by changing a body shape coefficient and a pose coefficient in the parameterized human body model; and replacing the vertex mapped three-dimensional Gaussian point cloud in the editable three-dimensional Gaussian model to realize texture editing. Compared with the prior art, the method solves the problem that personalized editing cannot be carried out on the human body model based on three-dimensional Gaussian splashing in the prior art.

The invention discloses an aerosol cross-regional transmission and infection risk assessment method in a medical building and application, and relates to the technical field of public health, and the method comprises the steps: constructing a medical building model and calculating a human body model; performing grid division on the medical building model and the calculation human body model to obtain a grid medical building model and a grid calculation human body model; performing steady-state simulation based on the gridding medical building model and the real environment data to obtain an initial airflow field in the gridding medical building model; performing transient simulation based on the gridding medical building model, the gridding calculation human body model, the initial airflow field and the personnel motion function to obtain aerosol distribution in the gridding medical building model; and performing infection risk assessment based on aerosol distribution to obtain an assessment result. According to the invention, cross-regional aerosol transmission in a medical building can be accurately simulated, and infection risk assessment is further carried out.

The invention discloses a generative digital human-oriented human body model relighting method, which belongs to the technical field of digital human relighting rendering and comprises the following steps of: reconstructing a human body model of a digital human in any posture by adopting a mixed representation mode of combining an explicit triangular mesh and an implicit texture material field, enabling the human body model to comprise a triangular mesh with high-frequency texture detail information, a roughness map, a normal map and a diffuse reflection albedo map; and carrying out relighting on the human body model by combining the adjusted any environment illumination information, the camera visual angle and the shadow information predicted through the human body parts, so as to obtain a digital human rendering image under any posture and any illumination condition. Therefore, relighting of the human body model under different postures and different illumination conditions can be realized, and a high-reality digital human video is obtained.

The invention provides a human body image restoration method and product based on a diffusion model, and belongs to the technical field of image processing. The method comprises the steps that after an original image is acquired, a three-dimensional human body model of a target human body is generated according to the target human body in the original image; obtaining a depth map of the target human body according to the three-dimensional human body model of the target human body; and inputting the depth map of the target human body into a ControlNet model, and controlling an Inpainting Stable Diffusion model to redraw the image of the target human body in the original image by the trained ControlNet model so as to repair the image of the target human body in the original image. The invention aims to improve the generation quality of the human body image.

According to the human body model reconstruction and body measurement method and system based on three-dimensional Gaussian splashing, the 3D GS technology is adopted, a scene is modeled through a group of Gaussian ellipsoids, and therefore efficient rendering and reconstruction are achieved. Compared with a traditional neural implicit representation method, the rendering speed and the reconstruction quality of the 3DGS are remarkably improved. The method is not limited by specific postures of the SMPL human body parameterization model, and more complex and diversified postures can be processed. Therefore, a more vivid and natural human body model can be generated in applications such as virtual reality, animation and games. According to the method, multi-view depth supervision is introduced, depth information is obtained from multiple views, and the precision of the model is further improved by using multi-modal data. By obtaining the RGB images and the depth maps of the multiple visual angles at the same time, the quality of the reconstruction result can be effectively improved, and the method is used for measuring body parameters.

The invention discloses a 3D Gaussian-based dressing human body geometry and texture parameterization reconstruction method. The method comprises the steps of generating human body and clothing grids of each frame of an RGB video based on a human body parameterization model SMPL and a clothing parameterization model TailorNet; generating a subdivision grid based on the human body and clothing grid, and generating an initial 3D Gaussian ball by taking the subdivision grid as a reference; training a Gaussian estimation network, and rendering by using a linear skin and 3D Gaussian splashing method; a motion sequence is given, and a dressed human body under the motion sequence is rendered by using a Gaussian estimation network. The invention provides the dressing human body reconstruction method which is more fit with the clothing and the human body model, the dressing human body rendering result under the given motion sequence can be output after the network training is completed, and the real and natural clothing wrinkle geometry and texture can be reconstructed.

The invention relates to a single-image dressed human body reconstruction method based on posture guide diffusion and view angle consistency constraint, and belongs to the field of computer vision and graphic images. The method comprises the following steps: firstly, carrying out multi-view image generation on a single image in an input dressed human body data set by adopting posture guide diffusion to obtain a two-dimensional diffusion image of an invisible view angle; secondly, establishing a visual angle consistency constraint module, taking the input image and the diffusion image as bidirectional visual angle features, performing implicit geometric guidance in the normal direction of the SMPLX human body template, and respectively extracting three-dimensional space features corresponding to cross visual angles; and finally, fusing voxelization features and three-dimensional space features in the SMPLX human body template to carry out human body implicit reconstruction to obtain a dressed human body model. According to the method, the problems of low reconstruction quality, clothing detail missing and the like caused by insufficient input information of a single image can be effectively solved, and high-quality three-dimensional reconstruction of a dressed human body is realized.

The invention relates to the technical field of computer graphics and artificial intelligence, and discloses a meta-universe digital human generation method and system based on deep learning, and the method comprises the steps: constructing a neural radiation field human body model through multi-view video data, and learning a user behavior sequence mode; collecting sparse sensor data of the head and the hands of the user and generating a preliminary whole-body skeleton posture; calculating contact force feedback when the digital human interacts with the virtual environment through a differentiable physical engine; utilizing a reinforcement learning algorithm to optimize postures to meet physical constraints; performing multi-objective optimization and quality evaluation on the generated attitude; according to the method, the digital human postures which have personalized features and can naturally interact with the environment can be generated by using the consumer-level equipment, and the meta-universe interaction experience is improved.

The invention relates to the field of artificial intelligence, and provides a digital person generation method and device, a server and a storage medium, and the method comprises the steps: obtaining a reference image of a target person of a to-be-generated digital person, and obtaining a preset posture parameter sequence; generating a plurality of target human body images according to the reference image and the plurality of preset posture parameters; generating a human body grid model of the target person according to the reference image and a preset human body model, and initializing parameters of a Gaussian body based on the human body grid model to obtain an initial digital person; and based on a three-dimensional Gaussian splash algorithm, optimizing a Gaussian body in the initial digital person by using a plurality of target human body images to obtain a target digital person. According to the method and the device, the digital person generation efficiency can be improved and the digital person generation cost can be reduced under the condition of ensuring the digital person quality, so that an insurance company can make the digital person for each insurance agent at relatively low cost and time.

The invention relates to the technical field of medical health services, and discloses a health suggestion recommendation method and system based on a digital twin model, and electronic equipment. The adaptive feature types are set for different suggestion strategies, the current feature type and the current feature in the human body digital twin model are acquired, the target strategy is determined from the suggestion strategies according to the matching result between the current feature type and the adaptive feature type, and the target strategy is executed according to the current feature. Compared with an indifference suggestion strategy adopted for the human body digital twinborn model, the method has the advantages that the suggestion strategy conforming to the human body digital twinborn model is selected through different feature types of the human body digital twinborn model; therefore, when the health suggestions are recommended based on the human body digital twin model, the recommendation accuracy of the health suggestions is improved.

The invention discloses a garment generation model training method, a digital human garment generation method and hardware. The method comprises the following steps: acquiring a three-dimensional human body model of a three-dimensional digital human to be dressed; obtaining first section data, and processing the first section data based on the three-dimensional human body model to obtain a three-dimensional grid model of the initial garment and second section data corresponding to the three-dimensional grid model; acquiring clothing image data including clothing texture information, and generating target image data including target clothing texture information based on the clothing image data and the second section data; the target image data is used for generating three-dimensional clothes data for dressing the three-dimensional digital human with the three-dimensional grid model; and obtaining a description text which corresponds to the target image data and is used for describing the clothing, and training the clothing generation model based on the target image data and the corresponding description text to obtain a trained clothing generation model.

The invention relates to the technical field of safety performance testing, and discloses an anti-falling waistcoat protection performance testing method and system. According to the method, a bionic human body model is driven through a multi-degree-of-freedom impact simulation device, a standard test dummy wearing an anti-falling waistcoat is impacted in multiple preset postures including the combination of a pitch angle and a roll angle, and a real falling scene is simulated; a flexible piezoresistive sensor array embedded into the inner layer of the waistcoat is used for collecting dynamic pressure distribution data in real time, and an air bag unfolding time sequence image is synchronously recorded; calculating a pressure dispersion rate based on the pressure data, determining protection response delay in combination with image analysis, and generating an attitude adaptability evaluation index through a multi-attitude test result; and finally, executing a continuous inflation and deflation cycle test to evaluate the sealing performance and the sensor stability. According to the method, the dynamic protection performance, the airbag response efficiency and the long-term use reliability of the anti-falling waistcoat in a complex impact posture can be comprehensively detected, and the consistency of a test result and an actual protection effect is improved.

The invention provides a 3D modeling-assisted garment pattern making method and system, and relates to the field of garment design, and the method comprises the steps: building a fabric database according to the fabric data on the current market, and obtaining an initial 3D garment model of a garment; fitting simulation is conducted on the obtained initial 3D garment model on the human body model, parameters of the initial 3D garment model are adjusted according to the simulation result and the fabric data, and an optimal 3D garment model is obtained; splitting the optimal 3D garment model to obtain a corresponding cut-part model and a sewing sequence; cloth is cut according to the cut-part model, solid cut-parts are obtained, the solid cut-parts are sewn according to the sewing sequence, manufacturing and adjusting of the clothes are completed, the pattern is confirmed, and therefore pattern making of the clothes is completed. According to the 3D modeling assisted clothing pattern making method and system, high precision, high efficiency and low cost of clothing pattern making are achieved, and meanwhile the design freedom degree and the wearing comfort degree are improved.