231 results about "Digital human" patented technology

Optimization algorithms and techniques to predict and simulate motion and various performance of a digital human model. The human body is modeled as a kinematics system represented by a series of segments connected by joints that represent musculoskeletal joints such as the wrist, elbow, shoulder, clavicle and pelvis. Optimization tools are used to determine the rotation at each degree of freedom of each joint that minimizes a performance measure.

A digital human generation method and system, where the method includes: defining a digital human model, where the digital human model includes multiple dimensions of user profile models; acquiring multiple dimensions of data of a specific user that is from multiple data sources; and processing, based on the multiple dimensions of user profile models included in the digital human model, the multiple dimensions of data of the specific user that is from the multiple data sources, to generate multiple dimensions of user profiles corresponding to the specific user, where the multiple dimensions of user profiles of the specific user form a digital human corresponding to the specific user.

The invention discloses a digital human serial section image segmentation method based on geometric active contour target tracking, comprising the following steps: 1) inputting a first layer digital human serial section image which includes a target to be segmented; 2) initializing the target contour by intelligent scissors; 3) generating a target contour matching score image; 4) smoothening the target contour matching score image generated in step 3); 5) using a self-adopting geometric active contour model tracking to obtain the target contour of current layer; and 6) storing the target contour segmentation result of current layer, simultaneously taking the result as an initial target contour of next layer and returning to step 3) to continue the target tracking to obtain subsequent target contour. The digital human serial section image segmentation method can accurately and robustly segment the target contour of the digital human serial section image and simultaneously has the advantages of high automation level and processing of topology change of the target contour.

The invention relates to a digital human body three-dimensional reconstruction method based on a Kinect device. The method specifically includes the following steps that firstly, scanning is performed, and surface feature data are obtained; secondly, denoising preprocessing is performed on the surface feature data, and smooth depth information without noise is obtained; thirdly, rigid-body matching and non-rigid-body matching are sequentially performed on the depth information, and a three-dimensional model is obtained. According to the digital human body three-dimensional reconstruction method, the scanning time is short, the scanning process is simple, a hardware device needed in scanning is simple, coordination with other people or instructions learning in advance are not needed in the scanning process, the result geometric accuracy is high, the face structure, the clothes texture structure and the like are quite clear, due to a test, the system stability is high, a one-button mode is adopted in a whole system, a user does not need to set any parameter or change, a final result can be obtained as long as one button is pressed, the operation time is short, and a color map is automatically generated.

A computer-aided positioning and navigation system for dental implant includes a computer system having built therein a dental implant planning software and providing a 3D digital human tissues model to create an implant navigation information, a positioning assistive device including a body providing a positioning portion and a guide portion and a connection member carrying an optical positioning device, one or multiple optical capture devices, and a display device electrically connected to the computer system. The computer system controls the optical capture device to capture images and drives the display device to display a part of the content of the 3D digital human tissues model and the implant navigation information.

The invention provides an individualized clothing customization system and a method for realizing the centralized management of data of a digital human body model, thereby leading the clothing design to provide the individualized service for people by a communication network, leading a clothing processing enterprise to provide the individualized clothing customization service by the digital human body model and causing the clothing of the people to reach the very fit level.

A system and method for analysis of steps of action of a person in activity in an environment with potential occlusion and without the need to use of invasive equipment. Non-limiting implementations use posture registration and postural analysis based on an observation protocol that allows reconstruction, in a digital human simulation environment, of the adopted postures observed in a real time situation or by video.

The invention discloses a human anatomy interactive system based on virtual reality and relates to the field of medical treatment, medical science and human scientific research. The system is composed of a head-mounted type display device, a host system, a track system and a controller device. VR characteristics are utilized to establish a full-three-dimensional virtual environment, a complete 3D digital human anatomy structure is introduced into the virtual environment, and then the result is displayed in a virtual scene. The user can perform interactive operations including picking, rotating, hiding, and the like, on the model through the controller in the complete virtual scene, as being personally on the scene. Through the system, the user can be assisted in learning and researching, so that the teaching and researching efficiency is increased and the teaching and researching cost is reduced.

The invention designs an endoscope tracking and positioning and digital human dynamic synchronous display device based on a multi-sensor, which consists of an endoscope front end attitude acquisition module, a communication and control center, a magnet exciting coil module and a PC (personal computer) processing center. A micro multi-sensor system is arranged in a front end probe of an endoscope and comprises an MEMS (micro electro mechanical system) triaxial accelerometer, a three-axis gyroscope and a three-axis magnetic field sensor; sensor information changes can be detected in real time when a probe carrier of the endoscope rotates and moves; according to different endoscopic structures, periodicity of the sensor information is imported into the communication and control center in a wireless or wire communication way; the control center drives an external field coil periodically according to the algorithm requirements of tracking and positioning, processes the sensor information preliminarily at the same time and then imports the sensor information into a PC machine; and after positioning is performed in the PC machine, dynamic synchronous display on the endoscope is realized by using a digital human model.

The invention discloses a semantic-based audio-driven digital human generation method and system. The generation method comprises the following steps of obtaining a target audio and a first human faceimage sequence; performing feature extraction on the target audio to obtain corresponding audio features; inputting the audio features into a pre-trained semantic conversion network, and performing semantic conversion on the audio features by the semantic conversion network to obtain a corresponding semantic motion sequence which comprises a plurality of mouth semantic graphs; and acquiring to-be-rendered face images with the same number as the mouth semantic graphs based on a first face image sequence, shielding mouth areas of the to-be-rendered face images, performing face synthesis based on the mouth semantic graphs and the to-be-rendered face images, and generating a synthesized face sequence. According to the invention, conversion between audio and facial semantics is realized through the semantic conversion network, and accurate expression of mouth shapes is realized by utilizing the facial semantics.

The invention discloses a method and a device for determining a map interface. The method comprises the following steps: obtaining the track dimensionality portrait data of a target digital human, wherein the target digital human is generated by a system which generates the digital human and consists of a multi-dimensionality target user portrait corresponding to a target user, and the target user portrait is generated in a way that multi-dimensionality data from a plurality of data sources is processed; determining the map data of a target area, wherein the target area is a specific map area which needs to be presented to the user; and according to the track dimensionality portrait data of the target digital human and the map data, determining a tracing map interface, wherein the tracing map interface is used for showing the track characteristics of the target digital human in the target area. The method, which is disclosed by the embodiment of the invention, for determining the map interface determines the tracing map interface to show the track characteristics of the target digital human in the target area according to the track dimensionality portrait data of the target digital human and the map data, can automatically and flexibility provide personalized map service for users and improves user experience.

The invention relates to a digital tool applicable to medical research, clinic consultation, teaching in schools and personal somatosensory, in particular to a system for digital analysis of human body and pathology. The system mainly comprises a three-dimension human body model processor module, a pathology document storage module, a pathology data search and analysis module, a multimedia server, video output equipment (such as projectors, displays or touch screens) and the like. A windows Chinese operating system or an android operating system is taken as a main running platform of the system, data of skin, muscles, tissues, organs, bones, acupoints and the like of the human body are recorded into the system by means of a virtual digital technique, and accordingly, a user can do analysis, research and study on detailed structure of the human body comprehensively at 360 degrees through a human-computer interaction technique; as various pathology data of different portions of the human body are recorded into the system, the user can do comparison visually and finally realize study, research and judgment and analysis of pathology.

Method and system for displaying a digital human-like avatar in self-driving vehicles (SDV) including detecting a set of environmental data/characteristics in the vehicle surrounding area by sensors/cameras generating signals to be input for traditional machine learning classifiers on a computer vision module (CVM); receiving control system inputs from the sensors and processing actions to be performed; after receiving outputs from the control system, executing autonomous driving actions by an actuator system; and based on inputs from the CVM and a personalization module, combined with actions and car status information from the control system, generating a digital avatar performing human-like reactions/expressions/gestures to properly communicate/indicate the current and future actions of the SDV for external people on a SDV display device.

The invention discloses a personalized deformation method of a deformable digital human anatomical model. According to the personalized deformation method, anthropometric parameters and medical imagedata of a user are acquired as references and input into a digital human body model, so that the appearance of the deformed model and the shape of an internal anatomical structure become similar to those of the user, and an anatomical structure model for the user is generated, and the purpose of personalized whole-body anatomical structure modeling is achieved. According to the technical scheme, deformation is conducted according to anatomical form characteristic parameters of a user or a medical image guide model, and personalized deformation of the model can be achieved in a manual adjustment or automatic registration mode. Through the personalized digital human body model generated by the invention, valuable reference data can be provided for the fields of doctor-patient communication,analogue simulation, clinical diagnosis and the like.

The invention provides a data information transaction method and system. The method comprises the following steps: a server receives a query request, wherein the query request is sent from a data requester terminal and carries a query condition and the user characteristic identifier of a digital human which needs to meet the query condition, and the user characteristic identifier is a characteristic category identifier obtained through the classification of each piece of user characteristic information contained in the digital human; determining the digital human user characteristic information corresponding to the query condition and the user characteristic identifier to obtain a query result, and sending the query result to the data requester terminal; and receiving a purchase request sent from the data requester terminal, and finishing a transaction according to the purchase request. In the digital human, according to the query condition and the user characteristic identifier, the user characteristic information is queried, so that the query result is more accurate, and query efficiency is improved. Meanwhile, the user characteristic information is obtained in a transaction purchase way so as to be favorable for guaranteeing the legitimate interests and the information security of a practical terminal user.

The invention discloses a sleeping posture spine form testing method without interference with sleep. The sleeping posture spine form testing method without interference with sleep is characterized by comprising the following steps. Firstly, a digital human body model is constructed based on personalized human body size. Secondly, man-bed interface sunk shape data is abstracted based on a personalized human body in sleep so that a sunk shape data model is set up. Thirdly, the digital human body model and the human-bed interface sunk shape data model are matched so as to obtain sleeping posture spine form. The sleeping posture spine form testing method without interference with sleep overcomes the defect that a horizontal sleeping posture can not be tested with the prior spine form testing art. The digital human body model and the human-bed interface sunk shape data model are matched to carry out a sleeping posture spine form test and the method is suitable for testing and estimating all sorts of sleeping posture spine forms. The sleeping posture spine form testing method without interference with sleep overcomes the defect that a subject is required to keep a specific posture and position in the prior spine form testing art or a specific testing device is used for carrying out a test and can carry out a natural sleeping posture spine form test in all beds or bed cushions.

The invention provides an interaction method and device based on a vehicle-mounted digital person, and the method comprises the steps: obtaining a video stream, collected by a vehicle-mounted camera,of a person in a vehicle; performing predetermined task processing on at least one frame of image included in the video stream to obtain a task processing result; and according to the task processingresult, displaying a digital person on the vehicle-mounted display equipment or controlling the digital person displayed on the vehicle-mounted display equipment to output interactive feedback information.

The invention belongs to the technical field of nuclear power design, and particularly relates to a function analysis method for operational control under accident condition of a nuclear plant with a digital human machine interface. The method comprises the following steps of firstly determining a selecting rule of function modules in accident operation regulations, screening the functions in the accident operation regulations according to the rule, obtaining a lift of functions which need to be treated with modularization design, then, integrating and screening the information of the function modules to determine an information list of comprehensive display control function, and finally, arranging the information list of comprehensive display control function according to an arrangement principle. The function analysis method is used for designing a related accident regulation comprehensive display control function, providing comprehensive monitoring and control information needed in the accident management process for operators, and improving accident management efficiency so as to reduce risks caused by accidents.

The invention provides a display method and device for a digital human meridian and acupoint model. The method includes: obtaining three-dimensional digital information of the user's human body; matching the three-dimensional digital information of the user's human body with a standard human body meridian and acupoint model to generate a digital file of the user's human body meridian and acupoint model; converting the digital file of the user's human body meridian and acupoint model sent to the user's mobile terminal for display. The present invention can digitally display the user's personal meridian and acupoint models, solves the problem of inaccurate user searching for acupoints caused by individual differences, and can assist users to complete acupoint physical therapy.

A digitalized man-machine interactive system of micro-beam plasma welding is prepared for applying DSP digital signal processor and using and DSP chip TMS 320 F 240 to receive command issued by operator through keyboard, using monolithic computer to control output of display and utilizing character liquid crystal display module as display for displaying both parameter values and welding process information of micro-beam plasma.

The invention discloses a traditional Chinese medicine digital visualization system. The system comprises an infrared thermal imaging device and an infrared image workstation. The infrared thermal imaging device is used for collecting human-body heat radiation energy of an examinee; the infrared image workstation is used for adopting a bone-length measurement method for fitting human-body meridians and acupoints to a human-body thermal-state distribution image to obtain a traditional Chinese medicine digital human image according to a national standard meridian acupoint map and in combinationwith important body surface mark points of a human-body anatomical structure; then temperature data extraction, calculation and analysis are conducted on the traditional Chinese medicine digital humanimage to obtain a traditional Chinese medicine digital visualization analysis report. The invention further discloses a traditional Chinese medicine digital visualization method. By means of the traditional Chinese medicine digital visualization system, the standard meridian acupoints are fitted to the digital human-body thermal-state distribution image by means of the bone-length measurement method, the traditional Chinese medicine digital human image which better accords with the actual condition can be obtained, and an accurate quantitative basis is provided for subsequently utilizing theimage for data extraction calculation, and analysis to obtain the dialectical result according to traditional Chinese medicine theories.

The invention relates to a magnetic-resonance radio-frequency coil performance evaluation method, which comprises the steps of establishing a magnetic-resonance multi-channel radio-frequency coil model and starting the multi-channel radio-frequency coil model to produce an excited magnetic field; loading a digital human model in the multi-channel radio-frequency coil model; calculating the electromagnetic field of each coil channel in the multi-channel radio-frequency coil model when the digital human model is loaded; calculating the coil sensitivity of the multi-channel radio-frequency coil model according to the magnetic field of each coil channel; calculating the noise coupling matrix of the multi-channel radio-frequency coil model according to an electric field produced by each coil channel; calculating the signal-to-noise ratio of the multi-channel radio-frequency coil model according to the coil sensitivity and the noise coupling matrix. The magnetic-resonance radio-frequency coil performance evaluation method has the advantages that the actual measurement environment is not required to be established, the performance of magnetic-resonance radio-frequency coils can be conveniently and quickly evaluated and the manpower and the material resources are saved. Moreover, the invention additionally provides a magnetic-resonance radio-frequency coil performance evaluation system.

The invention belongs to the technical field of garments, in particular to a human body modeling method applied to a network fitting system. The method comprises the following steps: marking the upperlimbs and the lower limbs of a human body with specific patterns; then acquiring a human body image by a camera; recognizing special mark points on the image and obtaining mark values corresponding to all pixels, wherein an aggregate of the mark values are human body modeling data. The method for recognizing the parts of the human body is simple, has high accuracy, modeling precision and speed and clear human body part marks, effectively solves the main problem of a digital human body modeling technology based on an image sequence, is convenient for system recognition and can be used for a network online real-time fitting system.

The invention discloses a digital MRI atlas construction method, which comprises the following steps: obtaining physical parameter values of a plurality of MRI signals of each pixel in an MRI image, and constructing a multidimensional data matrix, that is, a virtual MRI digital object; with the virtual MRI digital object being as a scanning sample, carrying out virtual MRI data acquisition and image reconstruction to obtain a virtual MRI image; and with the virtual MRI digital object being as the scanning sample, carrying out virtual data acquisition of different sections through different imaging sequences and sequence parameters to obtain atlas in different weight, and carrying out reconstruction to obtain a two-dimensional or three-dimensional image. The method can break through an original atlas range, that is, with the virtual digital human body being as the scanning sample, virtual data acquisition and image reconstruction of the digital human body are carried out by simulating a real MRI scanner, the digital MRI atlas obtained after different devices (field intensity can be set), sequence and sequence parameters can be set at will can be obtained, and real-time virtual acquisition and reconstruction is realized to obtain standard MRI atlas.

The invention discloses a method and a system for arranging digital human-machine interface monitoring units. The method includes performing parameter coding on a plurality of human-machine interface monitoring units according to characteristic values of the monitoring units; creating initialization groups according to a sequence of the monitoring units after parameter coding is performed on the monitoring units; evaluating the groups by a process for calculating error probabilities on the basis of an objective function of a Bayesian network to acquire monitoring human error probabilities corresponding to the groups; judging whether the monitoring human error probabilities acquired by means of evaluating the groups tend to be stable or not, creating new groups which represent an evolved sequence of the monitoring units by a genetic hybrid algorithm if the monitoring human error probabilities do not tend to be stable, or terminating an evolution procedure if the monitoring human error probabilities tend to be stable; and comparing the monitoring human error probabilities which are acquired in multiple group evaluation procedures and correspond to the multiple groups, and selecting the group with the minimum monitoring human error probability as the optimal sequence of the human-machine interface monitoring units so as to acquire the optimal arrangement of the human-machine interface monitoring units.