137results about How to "Flexible interaction" patented technology

The invention discloses an upper limb movement rehabilitation training system and method based on a Kinect sensor. The system comprises the Kinect sensor and a computer carrying an upper limb movement rehabilitation training module. The Kinect sensor is connected with the computer through a data line and arranged above a computer display screen. The upper limb movement rehabilitation training module comprises a single-joint rehabilitation training module, a comprehensive rehabilitation training module, a grading module and a correcting module and can conduct upper limb single-joint training and comprehensive training of shoulders, elbows and wrist joints. Patients do not need to wear or operate any interactive devices and only need to face the Kinect sensor and finish rehabilitation training movement according to the words or voice prompt on the display screen. The Kinect sensor conducts position capture on the upper limb joints, records and feeds back space position information of the upper limb joints of the patients in real time, guides the patients to finish rehabilitation training through motion sensing interaction and corrects non-standard training movement. The training method is simple, easy to master, good in enjoyment and low in use device cost.

The embodiment of the invention discloses a user interaction system and method. The system comprises an interface display module, a three-dimensional positioning module and a calculation processing module. The interface display module is used for providing an interaction interface for a user. The three-dimensional positioning module is used for capturing three-dimensional positioning information of a user scenario and sending the three-dimensional positioning information of the user scenario to the calculation processing module. The calculation processing module is used for calculating the three-dimensional space relative positions of the user eyes and hands relative to the three-dimensional positioning module based on the three-dimensional positioning information of the user scenario and determining positions of interaction hot spots in the interaction interface based on the three-dimensional relative positions and the relative position relation between the three-dimensional positioning module and the interaction interface.

The invention relates to a modularized multi-level converter sub-module control and protection method. The control and protection method comprises the following processing modes: in four control models of a sub-module, executing different control and protection logics by using a sub-module controller; generating a sub-module internal interface output signal, detecting an input signal and diagnosing a plurality of faults; executing control and protection actions by using the sub-module controller according to an action priority level; detecting the voltage of an energy storage capacitor C by using the sub-module controller; and performing asynchronous serial communication between the sub-module controller and a valve-based controller. In the method, a complete and intelligent control and protection scheme is designed aiming at the structure of the modularized multi-level converter sub-module, the coordinated control and protection of the overall sub-module can be realized, so that the stable and reliable operation of the sub-module in a converter and the coordinated matching with an overall control and protection system of the converter are ensured.

The invention discloses an intelligent gesture and voice control system of a curtain and a control method thereof. The control system comprises a gesture collection unit, a voice collection unit, an identifying unit and an external equipment unit, wherein the gesture collection unit is used for obtaining a gesture movement of a user through a camera; the voice collection unit is used for obtaining a user instruction through a microphone; and after the identifying unit is used for respectively identifying and judging a gesture and a voice, information of two channels is integrated according to a time sequence relation of an identified information flow. The curtain can be operated according to an integrated result. According to the intelligent gesture and voice control system of the curtain and the control method thereof, gesture control and voice control can be independently used and also can be used in a combined manner, so that a user has more natural and harmonious experiences in intelligent home furnishing. The gesture and the voice are combined to control the curtain at the same time so that the problem caused by manually opening and closing the curtain in the existing family is reduced and the quantity of remote controllers in the family is reduced; and meanwhile, elderly people and children in the family, and disabilities can conveniently use the curtain.

The invention discloses a dynamic hand gesture recognition method based on self incremental learning of the hidden Markov model. The method includes the following steps that firstly, a hand gesture is detected and tracked; secondly, feature extraction and vector quantization are carried out; thirdly, model training and hand gesture recognition are performed; fourthly, incremental learning is performed. According to the dynamic hand gesture recognition method based on self incremental learning of the hidden Markov model, dynamic hand gesture operation by a hand gesture operator in front of a camera can be accurately recognized, the recognized hand gesture data can be applied to incremental learning of an original model to adjust model parameters. Thus, the original model can dynamically adapt to novel variation generated in future hand gesture data and high adaptability to adjustment and alternation of the hand gesture data can be achieved. Thus, the model can be adjusted continuously along with the hand gesture data and better robustness on the unknown hand gesture recognition in the future is achieved.

Three-dimensional digital image data comes from a stereographic imaging arrangement (501, 502, 1201) that takes a first raw image (601) along a first optical axis and a second raw image (602) along a second optical axis. The imaging arrangement (501, 502, 1201) has a maximum imaging depth (506) and a minimum imaging depth (505). It transmits the first raw image (601) and the second raw image (602) to a receiving device (1102) along with an indication of a disparity range between a maximum disparity value and a minimum disparity value. The maximum disparity value is a measure of a difference between locations in the first (601) and second (602) raw images that represent the minimum imaging depth (505). The minimum disparity value is a measure of a difference between locations in the first (601) and second (602) raw images that represent the maximum imaging depth (506).

The invention discloses a wearable three-dimensional gesture interaction system and a suing method thereof. The system consists of a micro projector, a common camera, a portable computer, and a group of simple and easy marks. The function of human-computer interaction by using gestures and a three-dimensional graphical interface is realized through simple and easy computer vision computation. In the wearable three-dimensional gesture interaction system, a three-dimensional graphical interface is more vivid and the interaction mode is more flexible through a projection screen marked three-dimensional graphical interface mode and a virtual mouse gesture. The wearable three-dimensional gesture interaction system has simple equipment and low cost and can meet the requirements on mobile equipment.

The invention discloses multi-touch system and method in the technical field of computer vision. The method includes: establishing spatial correspondence between a Kinect camera and a projection screen; allowing a computer to preprocess an image captured by the Kinect camera; extracting a hand image from the preprocessed image; acquiring coordinates and directions of fingers in the hand image by finger contact detection algorithm; tracking finger contacts by minimum distance first algorithm; recognizing the finger contacts by means of template matching to obtain corresponding operational information of the finger contacts; and transmitting the operational information to the computer which analyzes the operational information and controls corresponding operations for the image in the current screen according to analysis results. Man-machine interactive multi-touching is achieved by the Kinect camera detecting acts of human fingers on the projection screen, and replaces the mouse and keyboard, and the operation is well performed in a real-time manner. The projection screen needs to be planar only, and adaptability of screen operation is increased greatly.

An embodiment of the invention relates to the technical field of virtual keys and discloses an interaction method of a virtual key and terminal equipment. The interaction method of the virtual key comprises the steps as follows: when gesture operations on the virtual key are detected, operation data of the gesture operations are acquired; press force is sequentially compared with multiple pressure thresholds, when the press force is judged to be matched with the current compared pressure threshold, a tactile feedback signal is generated, and one tactile feedback is provided at the virtual key; the operation types of the gesture operations are recognized according to the operation data; an operation command corresponding to the gesture operation is generated according to the preset relation between the operation type and the operation command. The invention further discloses the terminal equipment. Multiple gesture operations are adopted and multifunctional operation of the virtual key is realized under the condition that the virtual key combines with the press force; a user can be assisted in perceiving whether the current gesture operation is accurate in combination with the timely and simulating tactile feedback, and thus misoperation is reduced.

The invention relates to a system for realizing cloud computing application interface integration and unified style display. The system comprises a server agent module and a JavaScript frame module, wherein the server agent module comprises an HTTP (hyper text transport protocol) submodule, a reverse proxy submodule and a content replacement submodule; the JavaScript frame module comprises an event submodule, an Ajax submodule, a sand box submodule, a base submodule and a renderer submodule. According to the system and method for realizing cloud computing application interface integration and unified style display, the defects that multiple system interfaces are non-uniform in styles and the interfaces are limited through JavaScript interaction in the prior art can be overcome, a unified interface through which an agent module is not needed to be provided by integrated application and a flexible JavaScript interaction high-response speed interface access effect is achieved is provided, various cost input of the application integration is reduced, more mistakes of code logics are avoided, and the system is suitable for large-scale popularization and application.

The invention discloses a person-set mutual realization method of operation system emulation based on scanner, which comprises the following steps: (1) the customer sets the page through the network to connect server and scanner to enroll the server; (2) the scanner reads and operates the customer table program; the network table is established in the scanner; (3) the scanner downloads the mutual program and allocation data in the setting page; (4) the customer end analyzes the allocation data; (5) the mutual program reads the allocation data, which establishes the table manager; (6) the table manager establishes and allocates the table mutual element. The table mutual element contains speed pattern object, window object, task column and task column button object. The invention displays strong mutual function without any limit and refreshing the page, which improves the mutual function to the maximum limit.

In a method, a device and a computer program product for provision of protocols for configuration of a medical apparatus in the framework of a medical examination, the protocols are decentrally generated at a medical apparatus and are relayed to a central radiology information system. From the central RIS server the modified protocol can be relayed to arbitrary further instances via a network. The method employs a consistency mechanism which ensures that a set of protocols remains consistent and uniform given changes of one protocol.

The invention provides a photographing method based on augmented reality. The method includes a photographing step of photographing a real-world image; an information acquisition step of acquiring identification information and real-world action information according to the real-world image; a matching step of matching an interactive object from an interactive information base according to the identification information and matching interactive actions of the interactive object from the interactive information base according to the real-world action; and an image generating step of merging thereal-world image, the interactive object, and the interactive action of the interactive object to generate an augmented reality-based image. The technical scheme of the invention can meet the needs of a user to have a photo or interaction with stars or other characters, animals, or articles. In addition, the invention also provides a photographing apparatus based on augmented reality, a photographing device and a computer storage medium.

The purpose of the invention is to provide a method and a device for configuring a dynamic display effect of a virtual keyboard. The method comprises the steps of acquiring one or more initial elements to be configured; determining display regions, corresponding to the virtual keyboard, of the initial elements; determining movement loci corresponding to the initial elements to configure the dynamic display effect of the virtual keyboard. Compared with the prior art, the method and the device for configuring the dynamic display effect of the virtual keyboard are capable of flexibly configuring the dynamic effect for the virtual keyboard, and are good in expansibility, meanwhile the visual effect and the input experience of a user are improved and the individualized requirement of the user is satisfied.

The invention discloses a method and a system of combining three-dimensional line-of-sight tracking and brain-computer interface technology to control a manipulator to grasp an object. A process thereof includes: collecting line-of-sight signals of a user by an eye tracker, sending data to a controller, calculating three-dimensional coordinates of a gaze point by the controller, and sending the same to the manipulator; and at the same time, collecting human-brain electroencephalogram signal changes by an electroencephalogram helmet, sending the same to the controller, decoding user motion imagination and relaxation status by the controller, and thus triggering grasping and releasing action of the manipulator on the gaze object. According to the method and the system, the dual advantages ofhuman line-of-sight and mind control are exerted, the deficiency that existing 2D line-of-sight tracking technology must rely on a displayer is overcome at the same time, intuitive human-robot interaction can be carried out in a real scene, assisting or rehabilitating manipulators can be provided for paraplegic/hemiplegic patients, movement-inconvenient elderly persons and the like by applying the system of the invention, and autonomy thereof is improved or rehabilitation is helped in everyday life.

Provided is a pen interaction method based on handwriting input state adaptive judgment processing. In the process of carrying out hand-printed graphic inputting and hand-written character inputting by a user, the current input state of the user is automatically judged, real-time processing feedback is carried out, the user does not need to use a mouse or a keyboard or other interaction device to intervene, display state switching is not needed, and the interactive intention is expressed smoothly. The method defines the character input gesture, and the gesture not only differs from other basic graphs, but also has the ambiguous definition with the basic graphs forming the composite graph. The designed character input state judgment processing method and the note position judgment method can automatically judge the note input states and the note positions of the independent character object or the aiming symbol. The method can simplify the user operation procedures, the user can finish the pen interaction naturally and efficiently, certain universality and extendibility are achieved, and the method can be applied to the professional fields such as pen-interactive-based mechanical aided design and command and control.

The invention provides an electronic handwriting pen for identifying finger pen scratching and knocking actions, which comprises a pen shell and is characterized in that a pressure sensor group is embedded on the pen shell; a main control module, an A/D (Analog/Digital) converter, a power supply module and a wireless transmission module are arranged in the pen shell; the pressure sensor group is connected with the main control module through the A/D converter; the main control module is connected with the wireless transmission module; and the power supply module is connected with the main control module and the wireless transmission module. The electronic handwriting pen has the beneficial effect that the command operation can be realized through the scratching and knocking actions of a finger.

Disclosed are a multi-screen interaction method and device. The method comprises: sending, by a first terminal, a sharing message to a plurality of second terminals in a current interactive terminal list which is saved thereby, the sharing message carrying the content that the first terminal will share; when a control request sent by any one of the plurality of second terminals is received, determining whether a terminal which controls the first terminal exists currently, the control request being used for requesting to control the first terminal; if the terminal which controls the first terminal exists currently, sending a first control failure response to the second terminal which sends the control request; and if the terminal which controls the first terminal does not exist currently, sending a first control success response to the second terminal which sends the control request. By means of the solution provided in the embodiments of the present invention, the flexibility of interaction between terminals is improved.

The invention provides a multi-unmanned system supervision and control station and method based on MAS. The multi-unmanned system supervision and control station based on the MAS includes a parallel system architecture; the parallel system architecture includes a multi-agent software and hardware supervision and control system and unmanned systems; the multi-agent software and hardware supervisionand control system includes a hardware platform and a software platform; the hardware platform includes a multi-screen workstation; and the multi-screen workstation is provided with a dynamic physiological collection component capable of detecting operator physiological data and dynamic instructions. By using the multi-unmanned system supervision and control station based on the MAS, the real-time working state, environment complexity, task complexity and comprehensive intelligence information of the unmanned system are effectively monitored; the control mode of the unmanned system is calculated according to the environment complexity, the task complexity, the fatigue of the operator, and the autonomous level of the unmanned system, so that the control mode dynamic switching of the unmanned system is realized; and the human-machine hybrid intelligence is formed by a hybrid autonomous mode that is observable, interpretable and predictable, and can be intervened. The multi-unmanned system supervision and control station based on the MAS is applied to the field of supervision and control.

The present invention provides a one-dimensional input signal-based text input method and an electronic device. The electronic device comprises a display device that can be operated to show a cursor and a soft keyboard. The soft keyboard comprises letter keys. The method may comprise the steps of showing multiple cursors simultaneously on the soft keyboard, and positioning the multiple cursors on multiple keys on the soft keyboard; responding to an action of a user controlling the cursor to move, so as to enable the multiple cursors to move on the keys of the soft keyboard; responding to a confirmation selection operation of the user, wherein all keys selected by the cursors are selected simultaneously; showing candidate words on the display device according to keys continuously selected by the user; and determining the candidate word according to the user selection so as to input the word. Through adoption of the one-dimensional input signal-based multi-cursor text input method, a moving distance in inputting by the user is remarkably reduced, so that the input speed and efficiency are improved.

The invention discloses a dynamic extensible convolutional neural network accelerator, and belongs to the technical field of calculation, calculation and counting. The accelerator comprises an adaptive data storage module and an efficient computing array scheduling module. The adaptive data storage module comprises a hierarchical storage module and an external two-dimensional data conversion customization interface module. The efficient computing array scheduling module comprises a neuron processing unit array data scheduling module based on multiply-add logic and a neuron processing unit array data scheduling module based on a lookup table. The whole convolutional neural network accelerator masks the data delay of external memory access by designing a reasonable multi-level storage structure. Data scheduling is carried out on the computing array according to network layer characteristics and task requirements, so that repeated utilization of the data can be realized, the access parallelism degree of a lookup table of the computing array is improved, the operation speed is increased, and the accelerator can adapt to various complex computing tasks.

A method provides closed-loop control for an entire power supply system which has three supply levels each considered to be a separate regulatory unit and controlled independently of the other supply levels. An interface between two respective regulatory units is defined by control of the active power and reactive power transmitted between the two regulatory units. Appropriate control of the active power and reactive power transmitted between the regulatory units allows these regulatory units to be isolated from or connected to one another in terms of power. A power supply system is ideally regarded as a chain of separate regulatory units for supplying power. This allows efficient and safe operation and local control of a power supply system to which locally produced power is supplied, for example on different supply levels. In addition, a low number of data items to be interchanged between the supply levels is maintained.