109 results about "Virtual body" patented technology

The invention provides a hardware neural network conversion method which converts a neural network application into a hardware neural network meeting the hardware constraint condition, a computing device, a compiling method and a neural network software and hardware collaboration system. The method comprises the steps that a neural network connection diagram corresponding to the neural network application is acquired; the neural network connection diagram is split into neural network basic units; each neural network basic unit is converted into a network which has the equivalent function with the neural network basic unit and is formed by connection of basic module virtual bodies of neural network hardware; and the obtained basic unit hardware networks are connected according to the splitting sequence so as to generate the parameter file of the hardware neural network. A brand-new neural network and quasi-brain computation software and hardware system is provided, and an intermediate compiling layer is additionally arranged between the neural network application and a neural network chip so that the problem of adaptation between the neural network application and the neural network application chip can be solved, and development of the application and the chip can also be decoupled.

A system for configuring a prosthetic limb for use by a living being is provided. The system includes an electronic control unit (ECU) configured to receive a control signal generated in response to a command from the living being and to generate a plurality of virtual bodies on a display including members of a virtual prosthetic limb and at least one virtual object. The ECU is further configured to control movement of at least one member of the virtual limb responsive to the control signal, to determine a contact force between first and second virtual bodies of the plurality of virtual bodies upon engagement between the first and second bodies caused by movement of one of the one member of the virtual limb and the at least one virtual object and to adjust a position of at least one of the first and second bodies responsive to the contact force.

The invention discloses a method for achieving industrial robot off-line programming based on three-dimensional modeling software. The principle of the method is that a three-dimensional modeling software application programming interface (API) which is suitable for COM or object linking and embedding (OLE) and the like is used in the three-dimensional modeling software environment, model and space matrix data in the three-dimensional modeling software are obtained, a robot virtual body model and a mathematical model are built, and a virtual robot motion control system is realized; discretization from a curve to a point is conducted through obtained space line data, and therefore a motion trail of a robot is generated, actual robot operation is simulated; and an industrial robot controller operational procedure generating module is built, an actual controller executable file is generated and lead out so as to be operated in an actual robot controller, and industrial robot off-line programming can be achieved. The method can achieve off-line programming operation rapidly and generate optimal gesture of corresponding points automatically, time for generating training data is short, and a space curve trail can be achieved conveniently and rapidly, wherein a basis of the space curve trail is difficult to find in reality to conduct teaching.

Manufacturing processes profit greatly from a close collaboration between human and machine. Whereas a human behaves flexibly and adaptively but is inclined to make mistakes during repetitive work operations, machines operate quickly and exactly but are static and not very flexible. In order to enable an improved hazard protection in the context of a safe human-machine interaction, a spatial- and time-dependent variable degree of hazard is allocated to monitored spatial areas as a function of the current position and the current movement state of a machine or a machine element, as well as of the observed person. For this purpose, a multicamera system is used to acquire image data of the person in order to obtain the most detailed information possible about the position and alignment of a person, in particular also with reference to the body parts thereof, in an industrial environment. These image data are then examined with regard to the imaging of a person so that whenever a person has been detected in the image data, an articulated virtual 3D model of the human body is matched to this person hypothesis. Subsequently, this virtual body model is continuously matched to the movement behavior of the person detected in the image data. A hazard potential is determined using knowledge of the position and the movement behavior of the virtual body model in space. The hazard potential thus determined is subjected to a threshold value comparison in order to act upon the movement control of the machine or the machine part in the event of this threshold value being exceeded.

A computer method for simulating motion of at least a portion of a virtual body is disclosed. The method comprises the steps of: providing a surfaced body model; capturing or computing motion data for an external surface of the surfaced body; dividing the body model into at least two volumes, one of the volumes comprising at least a portion of the external surface of the surfaced body and being a deformable volume, and one of the volumes being a prescribed motion volume, the two volumes defining an interfacial surface; moving the external surface of the surfaced body according to the motion data while computing motion of the interfacial surface; and, simulating motion of the portion of a body by driving motion of the interfacial surface through the computed motion to provide an accurately positioned moving deformable surface that can be used in garment design.

A system and method is provided for facilitating navigation techniques in a three-dimensional virtual environment. The present invention couples input driving techniques to the state of one or more workspace variables (e.g., object state, virtual body state, environment state) to change the user's viewing context within a single input control motion. Modification of the user's viewing context allows navigation to various positions and orientations with out the need to be provided with that viewing context prior to navigation. The modification of the user's viewing context also allows for single input motion employing the same input drive controls.

The invention relates to a three-dimensional virtual dressing method of clothes for a real person, relating to the technical fields of digital clothing design. The system is characterized in that an object of the three-dimensional virtual dressing of the clothes is three-dimensional real-person body model structured according to the three-dimensional measuring data of the real person. A three-dimensional body measuring system measures the data of the real-person body of a consumer, the figure curve characteristic and the face characteristic, and guides the data into a three-dimensional dressing system; the original standard body model of the three-dimensional dressing system is corrected according to the data of the real person in the three-dimensional dressing system, and the three-dimensional real-person body model is showed virtually so as to lead the virtual body model to embody the figure characteristic and the face characteristic of the real person; the consumer and a designer decide the style, the fabric and the color design data by two-way selection, guide the data into a tailor-making system, complete the design of clothes and generate individual clothes sample pieces automatically; ready-made clothes are sewn virtually, and when the clothes are worn on the three-dimensional real-person body model, the individual dressing effect is intuitively displayed; and the design level and design efficiency of clothes are greatly improved.

This invention relates to one three-dimensional virtual body automatic generation method based on body part module and outline, which comprises the following steps: according to frame special property cutting the body into three sections for breast section, waist section, bug section; on this base, analyzing each section into one set of relative key sections to reflect the geometry shapes of sections as body parts; any one 3D virtual body forming can be as body module to modify and resemble the body outline.

The invention discloses a cervical cell image segmentation method based on an antagonistic generation network, comprising the following steps: a cell image is coarsely segmented, wherein for the cellimage coarse segmentation, a threshold method and a watershed algorithm are used for coarse segmentation of an original image to form guiding factors, and the original image is cut into small images;a virtual body segmentation image is generated, wherein the generated virtual body segmentation image is generated by using an antagonistic generation network designed in combination with a self-encoder, taking a clipped small image as an input, and using the guiding factors to help the neural network to locate a region of interest; a solid cell image is extracted, wherein the solid cell image extraction refers to that a real cell image is extracted from the clipped small image according to the virtual body segmentation image. The cervical cell image segmentation method based on the antagonistic generation network provided by the invention is the first time to use the antagonistic generation network to solve such problems, provides a novel automatic cell image segmentation method, and simultaneously solves the component loss in the traditional overlapped cell segmentation method.

The invention discloses a dance training system which comprises a somatosensory collection unit, an image processing unit, a storage unit and a display unit. The somatosensory collection unit is used for collecting limb movement images. The image processing unit is connected with the somatosensory collection unit, and is used for compositing limb movement images with virtual body images to form body dancing posture images. The storage unit is used for storing virtual standard dancing posture images. The display unit is connected with the image processing unit, and is used for comparing the body dancing posture images with the virtual standard dancing posture images and displaying body dancing posture movement errors. The dance training system has the advantages that by the dance training system, dancers can practise dancing independently without going out, nonstandard dancing postures can be corrected, and bodies can be exercised.

A method for locating external surface impacts on a body. The steps are: modeling the body in a control unit first database to obtain a virtual body model in a virtual system of reference axes; modeling, in a second database, a plurality of clouds of points in the virtual system, each cloud defining an inspection zone representing an external surface portion; selecting an inspection zone; transfering the coordinates of each point of the first and second databases to a geographic system of reference axes; determining geographic coordinates of an initial position of a range finder equipped flying drone communicating with the processing unit; calculating a drone flight plan to scan the selected inspection zone; creating a 3D meshing of the scanned inspection zone; detecting the impacts by comparing the 3D meshing and the virtual aircraft model and calculating the coordinates of each impact in the geographic and virtual systems.

A system for configuring a prosthetic limb for use by a living being is provided. The system includes an electronic control unit (ECU) configured to receive a control signal generated in response to a command from the living being and to generate a plurality of virtual bodies on a display including members of a virtual prosthetic limb and at least one virtual object. The ECU is further configured to control movement of at least one member of the virtual limb responsive to the control signal, to determine a contact force between first and second virtual bodies of the plurality of virtual bodies upon engagement between the first and second bodies caused by movement of one of the one member of the virtual limb and the at least one virtual object and to adjust a position of at least one of the first and second bodies responsive to the contact force.

The invention discloses a learning and playing method by means of a virtual musical instrument. The method includes that a laser and a camera are used to acquire the user's body image information, the body image information is transmitted to a host, by means of AR, VR, motion sensing game technology, a real body controls a virtual body in a virtual world displayed by a projector or a display screen 5 in a cross-eye manner to operate the virtual world musical instrument, or the host determines the physical movement positions of the real body so as to control the virtual body to operate the musical instrument displayed beside the virtual body. The invention further discloses a learning and playing device by means of a virtual musical instrument, the device includes a pair of glasses or a helmet, 1 refers to a host (mobile phone system, CUP, GPU, ROM, RAM, harddisc, external memory, bluetooth, wireless connection, and battery etc.), 2 refers to a loudspeaker, 3 refers to a laser, 4 refers to a camera, 5 refers to a projector or a display screen, and 6 refers to a microphone.

A field effect transistor (FET) and method of forming the FET comprises a substrate; a silicon germanium (SiGe) layer over the substrate; a semiconductor layer over and adjacent to the SiGe layer; an insulating layer adjacent to the substrate, the SiGe layer, and the semiconductor layer; a pair of first gate structures adjacent to the insulating layer; and a second gate structure over the insulating layer. Preferably, the insulating layer is adjacent to a side surface of the SiGe layer and an upper surface of the semiconductor layer, a lower surface of the semiconductor layer, and a side surface of the semiconductor layer. Preferably, the SiGe layer comprises carbon. Preferably, the pair of first gate structures are substantially transverse to the second gate structure. Additionally, the pair of first gate structures are preferably encapsulated by the insulating layer.

An embodiment of the present invention provides a virtual reality terminal and its visual virtualization method and device. The method includes: according to the wearing posture data of the virtual reality terminal in the actual physical space and the actual body shape data and actual action data corresponding to the user, Constructing virtual body shape data and virtual action data in a three-dimensional virtual scene; generating corresponding virtual display images according to the constructed virtual body shape data and virtual action data. When using the virtual reality terminal provided by the present invention, the user can use the reference object to generate the feeling of being on the scene from the first-person perspective, which improves the feeling of being on the scene, and can devote himself more wholeheartedly to the entertainment experience of the virtual world. It greatly improves the user's recognition of the reality of the virtual scene.

Methods for generating and sharing a virtual body model of a person, created with a small number of measurements and a single photograph, combined with one or more images of garments. The virtual body model represents a realistic representation of the users body and is used for visualizing photo-realistic fit visualizations of garments, hairstyles, make-up, and / or other accessories. The virtual garments are created from layers based on photographs of real garment from multiple angles. Furthermore the virtual body model is used in multiple embodiments of manual and automatic garment, make-up, and, hairstyle recommendations, such as, from channels, friends, and fashion entities. The virtual body model is sharable for, as example, visualization and comments on looks. Furthermore it is also used for enabling users to buy garments that fit other users, suitable for gifts or similar. The implementation can also be used in peer-to-peer online sales where garments can be bought with the knowledge that the seller has a similar body shape and size as the user.

The embodiment of the invention provides a digital twinning method and system based on a graph database. The method comprises the steps of obtaining entity information description data of each physical entity in a physical space; according to the entity information description data of each physical entity, identifying a domain model of the model database through a domain model identification algorithm to obtain a target domain model of each physical entity, and constructing a digital virtual body of the corresponding physical entity according to each target domain model; and storing the modelrelationship between the target domain models and the virtual body relationship between the digital virtual bodies into a graph database so as to construct the digital twinning based on the graph database. According to the embodiment of the invention, the domain model of the physical entity can be quickly identified, so that the data twinning based on the graph database is established, the construction efficiency and retrieval application efficiency of the domain model are improved, and the construction process of the digital twinning is simplified.

The invention discloses an intelligent wardrobe and an intelligent fitting management method, comprising: a wardrobe body; a 3D scanning device for scanning the style information and feature information of clothing and recording them into a cloud server; a driving device for driving the clothing to be sent to a specified location; cloud server, used to store the style information and feature information of the user's clothing, and perform big data analysis based on the user's daily wear; virtual projection area, used to establish a 3D virtual model of the clothing and match it with the user's body virtual model , realize 3D virtual fitting, and can adjust different virtual scenes, so that the 3D virtual model of the human body in the fitting can be placed in various scenes to view the effect of clothing trial. The present invention can obtain the data information of each piece of clothing in the closet, and correspondingly generate a 3D virtual model. When people need to choose clothes, the 3D virtual model of the clothing is matched with the 3D virtual model of the user's body to realize virtual fitting and save money. It's time to choose clothes.

The invention provides a preparation method of high-melting-point Kelvin structure lattice metal based on laser additive manufacturing, and belongs to the technical field of additive manufacturing oflattice metal. Based on a selective laser melting technology, the preparation method comprises the steps that hole pattern structure process adaptability design is carried out on the Kelvin structurelattice metal to establish a three-dimensional model of the Kelvin structure lattice metal; and slicing discretization treatment is carried out and layer-by-layer selective laser printing is carried out to obtain the Kelvin structure lattice metal. The Kelvin structure lattice metal is of a three-dimensional structure formed by expanding basic units, prisms of the Kelvin structure lattice metal units are entities, the other parts except the prisms are virtual bodies, and every two adjacent Kelvin structure lattice metal units share one prism. Through geometric parameter design, geometric parameter boundary setting and precise regulation and control of process parameters of selective laser melting of the Kelvin structure lattice metal, the high-melting-point Kelvin structure lattice metal with a fine structure is prepared.

The invention discloses a soft tissue deformation modeling method based on virtual springs. The soft tissue deformation modeling method based on virtual springs is based on the spring-particle model to establish an improved real-time deformation model of soft tissue, virtual body springs are added by the topological structure soft tissue surface model combining the square and the isosceles right triangle, so that a more real deformation effect is achieved; at the position of each particle in the system, the superposition of surface springs variable is equivalent to the surface deformation of an object, the resultant force of the elastic forces of the virtual springs is equivalent to the contact force on the surface of the object; the model inherits the advantages of the classical spring particle model that the principle is simple, the model is easy to establish, the calculation speed is quick, at the same time, the model has an ability to control the deformation area.

The invention discloses a time traveling method. The method comprises steps of pre-storing EEG signals produced by human feelings recorded by EEG in a host (1), generating a virtual body in 3D space, acquiring reality body image information via a laser and a camera (4) to transmit the information to the host (1), controlling the virtual body via VR and motion sensing game software of the host (1), analyzing according to virtual body actions by the host (1), and transmitting EEG signals corresponding to feelings to a brain stimulating module (3) to stimulate a user brain sensing area to produce touch, smell and taste feelings. The virtual body is formed via 3D human body scanning. The invention further discloses a time-traveling apparatus comprising a pair of glasses or a helmet, the host (1) (can be a cell-phone system, a CPU, a GPU, a ROM, a hard disk, an external memory, a Bluetooth, a wireless connection and a battery, etc.), a loudspeaker (2), the brain stimulating module (3), the laser and camera (4), a projector or a display screen (5) and a microphone (6).

The invention relates to a virtual social contact method based on Avatar expression transplantation. The virtual social contact method comprises the following specific operation steps: 1, extracting face feature points from a video stream input in real time by using an SDM (supervised descent method); 2, taking the facial semantic features as the input of a DDE (Displacement Dynamic Expression) model trained by CPR (Cascaded Pose Regression), and transplanting the output expression coefficients and head motion parameters to an Avatar (Virtual Body); 3, performing expression code grouping and emotion classification on the expression coefficients output by the DDE model; and 4, realizing expression animation audio synchronization through a network transmission strategy. According to the virtual social contact method based on Avatar expression transplantation, the facial expression of the user can be captured in real time; the expression replay can be carried out on the Avatar; and the virtual social contact of the network communication technology can be established.

Methods for generating and sharing a virtual body model of a person, created with a small number of measurements and a single photograph, combined with one or more images of garments. The virtual body model represents a realistic representation of the users body and is used for visualizing photo-realistic fit visualizations of garments, hairstyles, make-up, and / or other accessories. The virtual garments are created from layers based on photographs of real garment from multiple angles. Furthermore the virtual body model is used in multiple embodiments of manual and automatic garment, make-up, and, hairstyle recommendations, such as, from channels, friends, and fashion entities. The virtual body model is sharable for, as example, visualization and comments on looks. Furthermore it is also used for enabling users to buy garments that fit other users, suitable for gifts or similar. The implementation can also be used in peer-to-peer online sales where garments can be bought with the knowledge that the seller has a similar body shape and size as the user.