32 results about "Inertial motion capture" patented technology

A highly miniaturized electronic data acquisition system includes MEMS sensors that can be embedded onto moving device without affecting the static / dynamic motion characteristics of the device. The basic inertial magnetic motion capture (IMMCAP) module consists of a 3D printed circuit board having MEMS sensors configured to provide a tri-axial accelerometer; a tri-axial gyroscope, and a tri-axial magnetometer all in communication with analog to digital converters to convert the analog motion data to digital data for determining classic inertial measurement and change in spatial orientation (rho, theta, phi) and linear translation (x, y, z) relative to a fixed external coordinate system as well as the initial spatial orientation relative to the know relationship of the earth magnetic and gravitational fields. The data stream from the IMMCAP modules will allow the reconstruction of the time series of the 6 degrees of freedom for each rigid axis associated with each independent IMMCAP module.

The invention discloses an inertial motion capture pose transient calibration method and an inertial motion capture system. The inertial motion capture system comprises a data communication module, one or more pose capture modules and a data terminal, wherein each pose capture module comprises a nine-axis sensor (and a microprocessor), and one of the pose capture modules is a reference module; and pose transient calibration is performed by establishing a relationship among a world coordinate system V(w), an object capture coordinate system and an installation coordinate system in the system. Through the method and the system, a user can transiently and quickly finish system calibration only by adopting a pose, and pose correction and automatic quick adjustment of a skeleton proportion of a virtual model can be performed in the calibration process, so that the matching degree of action nodes is increased, the problem of inconsistent skeleton proportions of the virtual model and an actual object is effectively solved, the actions of a captured object are highly recovered, and the precision of motion capture is improved; and the operation is simple, so that the action capture time is greatly shortened.

The embodiment of the invention discloses a hybrid motion capture system based on deep learning. The system comprises: an inertial motion capture module, which is used for acquiring inertial attitudeinformation of an object; an optical motion capture module, configured to acquire optical attitude information of the object; a communication module, configured to send the inertial attitude information and the optical attitude information to the analysis module; and an analysis module, which is used for fusing the inertial attitude information and the optical attitude information according to thepreset hybrid model to obtain the optimal motion estimation of the object. In this way, through the characteristics that inertial motion capture is unobstructed and optical motion capture data is accurate, and through deep learning training, a hybrid model which integrates the inertial motion capture and optical motion capture characteristics is obtained, ensuring the accuracy of the final data.

An inertial motion capture system capable of collecting and capturing the face expression of an object at the same time comprises at least one depth camera, multiple inertial motion collection nodes, a transmitting node, an aggregation node and a terminal. The depth cameras are connected with the transmitting node, the transmitting node is connected with the inertial motion collection nodes and the aggregation node, and the aggregation node is connected with the terminal. Compared with the prior art, the inertial motion capture system can effectively capture the limb motion and face expression of the human body at the same time. Meanwhile, because the single-person inertial motion capture equipment only needs one wireless receiving and transmitting module, compared with a traditional scheme needing 15-17 wireless receiving and transmitting modules, system complexity is reduced, data delay is reduced, and the data transmission rate is increased.

The invention discloses a human body posture motion capture algorithm based on heterogeneous data fusion. The algorithm comprises the following steps: (1) acquiring human body motion data by using a plurality of sensor node posture acquisition modules fixed at various feature parts of the human body, each sensor node comprising a three-axis accelerometer, a three-axis gyroscope and a three-axis geomagnetometer; (2) modeling signals of the accelerometers, the gyroscopes and the geomagnetometers respectively, and filtering and converting the signals; (3) calculating displacement rotation features in a three-dimensional space by using a complementary Kalman filter fusion algorithm, calculating the positions of limbs relative to the space in combination with the spatial displacement and rotation features, and mapping the calculated feature parameters to the corresponding limbs to drive the motion of the body in real time. The invention aims to develop an accurate and efficient multi-sensordata fusion algorithm to solve the problems of low precision, response lag and the like in the conventional inertial motion capture, and to provide some reference for the development of related fields.

The invention discloses a stage element centralized control system. The stage element centralized control system comprises a server and a display control terminal, wherein the server is connected with the display control terminal, the server is connected with a wireless control terminal through a wireless router, a large screen host computer is connected with the wireless router, an inertial motion capture system and an LED (light emitting diode) large screen, and the server is further connected with a DMX512 (digital multiplex 512) control platform, a PLC (programmable logic controller) centralized control system and a 232T0485 serial port. The stage element centralized control system integrates stage elements into a software control system, not only achieves control presetting and automatic execution in a time series for the stage elements, but also can switch to real time field control as needed whenever necessary, guarantees perfect and reasonable presentation of the stage elements in a performance process, intelligently and accurately controls video, voice frequency, lamplight, machinery, scenes and the like in a stage performance, and prevents faults or faulty operation from occurring. Additionally, the stage element centralized control system is convenient to carry and simple to use, and effectively reduces cost of the stage performance.

The invention discloses a rapid calibration method and a rapid calibration system for inertial motion capture attitude. The method comprises the following steps: acquiring attitude data of a capturedobject in a calibration attitude by using an attitude capture module; obtaining gravity acceleration and the degree of jitter of a wearing portion of the attitude capture module according to the acquired attitude data so as to adjust the attitude and the degree of jitter of the captured object according to the obtained gravity acceleration and the degree of jitter until the captured object poses as a calibration attitude and the degree of jitter of the captured object does not exceed a preset threshold; calculating to obtain a first transformation relationship according to the adjusted attitude data of the attitude capture module; calculating to obtain a second transformation relationship according to the adjusted attitude data of the attitude capture module and the first transformation relationship; and performing a first calibration on the attitude data output by the attitude capture module according to the second transformation relationship. The rapid calibration method and rapid calibration system for inertial motion capture attitude have the advantages of simple operation, high speed and high precision, and can be widely applied to the field of motion capture.

The invention relates to the technical field of stage control and especially relates to a stage integrated control system. The system comprises a control center. The control center is connected with astorage module and a display module through wires. The display module is used for displaying control data; the storage module is used for storing data processed by the control center. A light controlmodule is connected with a light device through a wire. The light control module controls illumination effect of brightness of a stage. A heating control module is used for adjusting working temperature of a stage fog device. The control center is connected with a big-screen host through a wireless transmission module. An inertial motion capture system is used for capturing stage dynamic pictures. An LED bog screen is used for displaying the real-time dynamic pictures of the stage captured by the inertial motion capture system. The system utilizes unified management and synchronous control, improves stage performance effect and work efficiency, and can adjust the operating temperature of the stage fog device.

The embodiment of the invention relates to the technical field of attitude detection. The invention discloses a motion capture method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining the angular speed of a first target limb of a first motion object at a current moment through inertial motion capture equipment, and predicting thefirst position information of the first target limb at a target moment according to the angular speed; then, determining second position information of the first target limb at the target moment based on a first preset optical mark point of the first target limb through optical motion capture equipment; then, according to the first position information and the second position information, determining the target position of the first target limb at the target moment so as to capture the action of the first target limb; according to the method provided by the embodiment of the invention, errorsand offsets introduced by inertial motion capture equipment can be reduced as much as possible, and the motion capture accuracy is greatly improved.

The invention provides a liyuan opera virtual reality reproduction method based on a motion capture technology. The method comprises the following steps: A1, segmenting a scene to be captured into a plurality of acquisition segments, and determining actions, line souvenir and music scenes of opera actors in the segments; A2, the opera actor wearing inertial motion capture equipment to perform, theacquisition equipment acquiring motion data of the actor in a three-dimensional space through the inertial motion capture equipment, and the recording equipment acquiring line souvenir data and background music data of the opera actor; A3, creating a three-dimensional figure model according to the physical signs of the opera actor to bind bones of the three-dimensional figure model; A5, combiningthe acquired fragments, driving the three-dimensional character model to perform virtual performance action by action data, and combining the line souvenir data and the background music data to forma drama performance virtual scene in the virtual reality scene. According to the invention, the traditional drama performance can be made into a virtual reality scene which can be watched by a virtualreality helmet with high precision.

The invention discloses a cerebral apoplexy rehabilitation training system based on virtual reality and inertia motion capture. The system comprises a motion capture device, a virtual reality man-machine interaction device and a feedback device; the motion capture device is in communication connection with the virtual reality man-machine interaction device, and the virtual reality man-machine interaction device is in communication connection with the feedback device. The novel treatment and rehabilitation system is explored on the basis of a virtual reality technology and a motion capture technology. The technologies replace the positions of traditional physicians, and labor is greatly saved. The virtual reality technology is used for gamification of the treatment process, so that the treatment is not boring any more. Besides, due to the addition of the novel technology, the treatment cost is greatly reduced.

The invention discloses a VR mirror image therapeutic instrument and belongs to the technical field of VR. The VR mirror image therapeutic instrument comprises a host computer, and a hybrid motion capturing system, a mirror image display, a doctor display and an input device connected with host computer. The hybrid motion capturing system comprises an inertial motion capturing module and an optical motion capturing module, the inertial motion capturing module cooperates with arms of a patient to capture motion of upper limbs, and the optical motion capturing module cooperates with palms of thepatient to capture motion of hands. The demonstrated therapeutic instrument has a more vivid mirror image effect, can improve a visual feedback effect greatly, quantity a treatment effect, and help adoctor to master the rehabilitation condition of the patient, and a treatment scheme can be made to make the treatment process standard.

The embodiment of the invention provides a human body action data acquisition method and device. The method comprises the following steps: collecting optical motion capture data, collecting inertial motion capture data, and calculating to obtain human body motion data by adopting the optical motion capture data and the inertial motion capture data, so that the finally obtained human body motion data is more stable, data errors caused by a single motion capture system is eliminated to a certain extent, and advantage complementation is formed at the same time; and obtaining more accurate human body motion data by combining the accuracy of the spatial position in visual information and the characteristics of high sensitivity and good dynamic performance of the inertial sensor.

The invention relates to a virtual interactive motion auxiliary system based on inertial motion capture equipment, and the system comprises a motion capture module which is used for constructing a 3D character model, collecting human body motion data, and transmitting the human body motion data to a human-computer interaction module; a heart rate measuring module which is used for collecting and processing heart rate data of a human body; a body fat measuring module which is used for collecting body fat data of a human body and processing the body fat data; and a man-machine interaction module which is a user interface integrating basic information acquisition, data analysis and monitoring, image display, a voice broadcast part and mode selection, adopts a Unity 3D platform, and is displayed on a display screen in a client form. The invention further discloses an auxiliary method of the virtual interactive motion auxiliary system based on the inertial motion capture equipment. The method is suitable for common people, is not limited to a certain type of people, and can be popularized to the public; The system has multiple functions, can reproduce motion actions in a virtual world, and also can carry out action error correction, body fat analysis, heart rate real-time monitoring and alarm.

The invention discloses a remote control system and method of a robot based on inertial motion capture. The remote control system of the robot based on inertial motion capture comprises a sensor aligning module used for initializing an inertia motion capture device, a motion capture module used for obtaining motion postures of all joints corresponding to a body according to data transmitted by aninertial sensor, a posture update module, a motion tracking module used for tracking user motions and obtaining user position changes and posture changes and a robot control module used for calculating displacement and angles needed by current robot movement according to user positions and posture changes. According to the scheme, the inertia sensor is utilized for capturing user motions. According to user motions, positions and posture changes of users are calculated. Then, displacement and angles needed by current robot movement are calculated by tracking user positions and posture changes.The robot can be remotely controlled to enter an environment to which mankind cannot be adapted and finish work. Therefore, damage to mankind is avoided.

The invention relates to the field of VR virtual technologies and particularly relates to an action capture digital asset management system. The system comprises an APP client, a peripheral server, asystem server and a display terminal. The APP client comprises a login end and a receiving end, wherein the login end is electrically connected with the system server; the receiving end is electrically connected with the system server; the receiving end is connected with the peripheral server through a signal; the system server is connected with the display terminal through signals. The display terminal comprises a signal module 4 which is in signal connection with the system server, and the signal module 4 is connected with a VR mode port and a 3D mode port. Compared with an optical motion capture technology, the inertial motion capture technology adopted by the invention has the advantages of low cost, high environmental applicability and the like; the inertial motion capture technologyis simple and easy to operate, and a user only needs to open an APP to enter the client, and therefore the action synchronization of a character and a virtual character can be realized.

The invention discloses a method and a device for correcting inertial motion capture deformation and distortion based on a large space. The device comprises a grid division unit, data collection equipment, a space positioning module, a data processing unit and a data correction server, wherein the data processing unit is connected to the data collection equipment, and is used for transmitting magnetic field data of grid nodes to the data correction server in a threading manner; the space positioning module is used for recording positioning information of the grid nodes; a magnetic field data storage module is used for recording magnetometer data inside a gyroscope at the position of each grid node; the data correction server is used for receiving data of the data processing unit and correcting the data of the gyroscope at each spatial position into spatial actual data and then transmitting the spatial actual data to a virtual character for matching. After the device and the method areadopted for correction, the body form in the large space becomes normal, the body form can remain unchanged accurately with arm actions of a tester, and the disadvantages of deformation and distortionare avoided.

The invention discloses a virtual reality multi-person interaction method and system. The system comprises a central processing unit, the central processing unit is electrically connected with an operation center, a wearable device, a computer and a three-dimensional scanning device, language acquisition and planar motion acquisition are arranged in the wearable device, image display and image rendering are arranged in the computer, and the three-dimensional scanning device comprises an optical scanning and inertial motion capture module. By arranging the central processing unit, the database,the operation center, the wearable device, the computer and the three-dimensional scanning device, a perfect virtual reality technology is formed, previous big data can be stored in real time, the data use time is prolonged, and the system is very practical.

The invention relates to an inertial arm action capture data fusion method. The method is characterized in that on the basis of a D-H model, a quaternion is used for representing human arm postures, and a human arm quaternion model is established for data fusion, so that computation burden is reduced; by the aid of a divided-state fusion algorithm, arm movement states are divided into a dynamic state and a static state according to angular speed data, and the angular speed data are used for fusion in the dynamic state while accelerated speed and magnetic flux data, which are low in fusion speed, are used for data fusion in the static state, so that the fusion computation burden is further reduced, and an inertial action capture system can be operated on an embedded platform.

The invention discloses a mutual calibration method based on alternating electromagnetic field positioning and an inertial sensor. The method comprises the steps: enabling one type of electromagneticfield radiator in a human body posture obtaining system to correspond to the inertial sensor, and enabling the type of electromagnetic field radiator and the inertial sensor to obtain the displacementinformation of a target at the same time; obtaining angle information of the electromagnetic field radiator relative to another electromagnetic field radiator based on a human body posture obtainingsystem; calibrating the angle information, obtained by the inertial sensor, in the horizontal direction of the target by utilizing the angle information; an inertial motion capture device is combinedwith an alternating electromagnetic field position calculation system; an alternating electromagnetic field position calculation system and inertia six-axis sensor angle calculation are used for mutual calibration, and the geomagnetic meter is replaced with angle information in one direction calculated by the alternating electromagnetic field position calculation system and the inertia six-axis sensor angle calculation, so that the inertia six-axis sensor obtains a long-term stable calibration basis, and respective problems are solved.

This application relates to the technical field of human motion capture, in particular to a sparse IMU real-time human motion capture and joint force prediction method and system, the method includes: collecting the left wrist, right wrist, left knee lower part, right knee lower part, Inertial data of the head and waist, get the bone orientation and acceleration of the bone in the human coordinate system, input the bone orientation and acceleration into the preset human kinematics model, predict the human body posture, motion, and human-ground contact information and input Based on the preset human dynamics model, it predicts human posture, movement, joint force and ground force, and solves the problem of hindering human movement by binding a large number of sensors for human motion capture and joint force prediction. The dual PD controller connects the human kinematics model and the human dynamics model, and integrates them into an overall sparse inertial motion capture and force prediction system, realizing reliable real-time human motion capture and joint force prediction.

The invention provides a motion capture-based virtual reality sign language learning, testing and evaluating method. According to the method, a motion comparison device is adopted to carry out datamation processing on a sign language session scene. The action comparison device comprises inertia action capture equipment, a data collector and a data comparison device. The inertial motion capture equipment comprises a plurality of data sensors. Each data sensor is bound and attached to a human body part of a session participant. When the sign language conversation scene is carried out, the data sensor records human body space movement information of the conversation participant to form conversation scene data and establishes a virtual reality scene by using the session scene data through a three-dimensional scene development platform. A sign language learner learns the sign language through the virtual reality scene. According to the invention, the action capture technology can be used torecord the sign language session scene and form the virtual scene. Therefore, the related functions of sign language learning, testing and sign language action evaluation are carried out by using thevirtual scene.

The invention provides a state prompting method and device for an inertial motion capture sensor. The method comprises the steps: generating a state indication signal according to the state of an inertial motion capture sensor; obtaining a corresponding lamp language instruction according to the state indication signal; and controlling a state indicating lamp to flash by adopting the lamp language instruction so as to display the state of the inertial motion capture sensor through the flash characteristic of the state indicating lamp. By the adoption of the state prompting method and device for the inertial motion capture sensor, motion capture personnel can determine the state of the inertial motion capture sensor only by observing the flashing state of the state indicating lamp; because the state indicating lamp can be deployed at various possible positions, the flashing state of the state indicating lamp can be conveniently and quickly checked as long as no middle shielding motion capture person exists, and the state of the inertial motion capture sensor is determined.

The invention provides a motion capture system and method based on laser large-space positioning and optical inertia complementation. The system comprises a positioning base station, a positioning piece and a processing unit. The method comprises the steps of: constructing a local area network through the Bluetooth, the WiFi and the server; fixing the positioning base stations to the four cornersof the positioning space to scan the positioning space, and matching the positioning piece to collect optical positioning data of a captured object, wherein the positioning piece is arranged on the body of the captured object, collects optical positioning data and inertial motion capture data of the captured object, transmits the optical positioning data of the captured object through Bluetooth, and transmits the inertial motion capture data of the captured object through WiFi; and the processing unit receives the optical positioning data and the inertial motion capture data of the capture object acquired and transmitted by the positioning piece in real time through Bluetooth and WiFi, and fuses and solves the pose information of the capture object. The system realizes large-space multi-person positioning and motion capture based on laser large-space positioning, optical and inertial complementary motion capture, IK whole-body attitude calculation and other technologies.