73 results about "Gesture analysis" patented technology

An apparatus and method change an icon in a portable terminal. The apparatus for performing an icon edit process in the portable terminal includes an input unit, a gesture analysis unit, a controller, and an edit-mode performance unit. The input unit receives an input of a gesture by a user. After sensing and analyzing the gesture input through the input unit, the gesture analysis unit identifies if the gesture is an edit gesture made on an icon. If the gesture is not the edit gesture made on the icon, the controller performs an operation for the gesture. If the gesture is the edit gesture made on the icon, the edit-mode performance unit performs an edit mode.

The invention provides an automatic gesture recognition method. The automatic gesture recognition method comprises the steps that each frame of source image in obtained gesture video data is converted into the YCbCr color space; skin detection is conducted by means of a skin color oval model; gesture division is accomplished by means of connected component analysis, edge detection and contour extraction; feature vector extraction is conducted through gesture analysis, and statistical characteristic parameters such as the image normalization rotational inertia and invariant moment characteristic, shape characteristic parameters such as the peripheral rectangular of a gesture, the direction of the gesture, the circumference of the gesture, the area of the gesture and the scale value of the gesture, and structural characteristic parameters such as the number of fingers and the fact that whether the thumb is included are selected to serve as parameters used for recognizing the gesture; gesture recognition is conducted by means of the template matching method based on Euclidean distance improvement. By the adoption of the automatic gesture recognition method, different gestures can be recognized efficiently, and man-machine interaction mainly based on the efficient, direct and natural gestures can be closer to the communication between people.

The invention discloses a method and a device for operating and controlling a virtual center console of a blind-operation-supported automobile by gestures. By the method and the device, a user can conveniently use gestures to perform corresponding operation and control on a center console touch screen during driving without transferring road driving sight line, and by an automobile blind operation function, the shortcoming of searching complex and various mechanical buttons in the conventional driving room to control the conventional automobile is well overcome; and meanwhile, the virtual center console integrates a gesture language library module, a gesture analysis and processing module, a gesture language recognition module, a gesture language library management module, a gesture operation and control execution module and a gesture operation and control security mechanism management module, and because of cooperative work of the modules, gesture language operation and control has the characteristics that the gesture language operation and control is easy and convenient to use, gesture operation and control windows are independent, gesture language meaning is unique, a gesture language can be modified, an operation and control mechanism is safe and the like, and convenient, rapid, friendly and safe operation and control experiences of the automobile center console can be brought to the user according to specific requirements.

Embodiments of techniques or systems for usage modeling or gesture based authentication are provided herein. Actions of a user may be captured, classified, and utilized to generate an authentication scheme for a device based on gesture recognition, gesture analysis, or action analysis. Training data may be determined based on actions deemed to be training actions and one or more action models may be generated based on the training data. An action model may be indicative of how a user performs a particular or predetermined action. When a security mode is enabled, usage actions may be recorded and usage data may be extracted or determined based on the usage actions. A usage action may be identified and corresponding usage data may be compared with training data from an appropriate action model. An identity of a user associated with the usage action may be determined based on this comparison.

The invention provides a playing scene synthesis enhancement control method and device. The method comprises the steps that firstly, a corresponding image of a preset virtual musical instrument is added into an audio and video stream acquired from a slave camera shooting unit and pushed to a direct broadcasting room; a user gesture acting on a playing control portion of the virtual musical instrument is recognized from the audio and video stream, the control state of the playing control portion is changed in an image stream of the audio and video stream along with the user gesture, audio configuration information corresponding to the virtual musical instrument is called, and an audio stream adapting to the control state of the playing control portion in the audio and video stream is generated; a synthesized audio and video steam including the image stream and the audio stream is pushed to the direct broadcasting room. The virtual musical instrument generation technology and the gesture analysis technology are combined, and virtual musical instrument playing direct broadcasting is carried out in the network direct broadcasting room.

A method for providing hand segmentation for gesture analysis may include determining a target region based at least in part on depth range data corresponding to an intensity image. The intensity image may include data descriptive of a hand. The method may further include determining a point of interest of a hand portion of the target region, determining a shape corresponding to a palm region of the hand, and removing a selected portion of the target region to identify a portion of the target region corresponding to the hand. An apparatus and computer program product corresponding to the method are also provided.

The invention discloses a digital image interactive method and system of a television. The digital image interactive method comprises the following steps: obtaining video signals; segmenting gestures from video signals; performing gesture analysis to generate gesture characteristic parameters; and recognizing the gestures according to the gesture characteristic parameters to generate gesture recognizing signals. The digital image interactive method and system is based on visual gesture recognition and collects the gesture information through a camera for recognizing. The digital image interactive method has the advantages that input devices are cheap, limitation on users is small, human hands are in natural state, and users can perform man-machine interaction in a natural method, and user experience of man-machine interaction is greatly improved. A motor is driven to perform various operations through the generated gesture recognition signals.

The invention discloses an infrared precise multi-point touch platform, which comprises a hardware system part and a software system part, wherein the hardware system part comprises an infrared transmitting tube array, a touch screen, a camera, a computer and a projector; the software system part comprises a contact tracking module and a gesture recognition module; the contact tracking module comprises an image processing sub module, a contact profile extracting sub module and a contact tracking sub module; the gesture recognition module comprises a multi-point touch gesture analysis and definition sub module, a gesture recognition and judgment sub module and a gesture driving sub module. The touch platform disclosed by the invention can realize human-machine intelligent interaction by returning infrared variation caught by the special camera and then locating in the computer; on the aspect of hardware, the touch platform has advantages of high recognition precision, low cost, simple structure, convenience in updating and the like, and on the aspect of software, the touch platform is characterized by being concise and easy in understanding of program, easy to operate, easy to expand, strong in transplanting, strong in adaptability, etc. on the aspect of software; and the touch platform can guarantee smooth coordination between software and hardware systems, and is easy to implement.

The invention discloses a screen operation control system, which comprises a gesture acquisition module, a gesture analysis module and a screen, wherein the gesture acquisition module is used for acquiring the gesture information of an operator, and transmitting the gesture information to the gesture analysis module; the gesture analysis module is used for analyzing the gesture information to determine a gesture of the operator, translating the determined gesture into a corresponding control instruction, and performing operation control on the screen according to the control instruction. The invention further discloses a screen operation control method. Compared with the prior art, the scheme can be implemented more flexibly and conveniently.

The invention discloses a gesture input system and method in 3D scene. The gesture input system comprises a gesture acquiring unit used for acquiring at least two channels of video stream data in real time for gesture of users respectively, a gesture identifying unit used for identifying gesture shapes changing in real time from the video stream data, a gesture analysis unit used for analyzing the gesture shapes changing in real time and acquiring the corresponding gestures, and a gesture display unit used for processing the gestures into 3D images to be displayed in the 3D scene in real time. Real gestures of the users can be displayed in the 3D scene in real time, real effect of the system is improved and user experience is enhanced.

The invention discloses a method and a device for operating video games by bearing gesture touch. The method comprises a bearing gesture operation flow, a movement direction control rule, a movement speed control rule, a game action execution rule, and a short-cut function calling rule. The device comprises a game terminal and a touch terminal, wherein the game terminal includes but not limited to an intelligent television, a pair of intelligent glasses, and an VR (virtual reality) helmet; the touch terminal includes but not limited to an intelligent mobile phone, an intelligent watch, and an intelligent ring; the touch terminal is provided with a touch screen; the touch screen is used for detecting bearing gestures; application programs are installed in the touch terminal and the game terminal; each application program comprises a data obtaining module, a data sending module, a data receiving module, a gesture analysis module, an instruction obtaining module, and an instruction execution module. The method and the device have the advantage that a user finger makes the bearing gestures on the touch screen of the touch terminal, so that the video game can be conveniently, accurately and quickly operated on the display screen of the game terminal in a blind way.

Provided is a vehicle control system. A vehicle comprises a storage unit, a touch unit and vehicle windows. The storage unit stores a corresponding relation table about preset gestures and action instructions, and the touch unit is used for responding to the touch gestures input by a user and generating input signals. The control system comprises a gesture recognition module for responding to the input signals and detecting the touch gestures according to the input signals, a gesture analysis module for comparing the touch gestures recognized by the gesture recognition module with preset gestures stored in the corresponding relation table and acquiring action instructions corresponding to the preset gestures consistent with the touch gestures, and a control module for controlling the vehicle window to rise or descend according to the action instruments acquired by the gesture analysis module, wherein the action instructions are used for controlling corresponding vehicle windows to rise when the touch gestures are touch gestures sliding in the first direction in the touch unit, and the corresponding action instructions are used for controlling corresponding vehicle windows to descend when the touch gestures are touch gestures sliding in the second direction in the touch unit.

The invention relates to an input device and an input method based on a multi-finger capacitive touch technology. The device is characterized by comprising a touch panel (1), a touch signal microprocessor (2), a gesture analysis module (3) and a communication module (4), wherein the touch panel (1) is used for receiving an input signal; the touch signal microprocessor (2) is used for receiving an output signal of the touch panel (1); the gesture analysis module (3) is used for analyzing the output signal of the touch signal microprocessor (2); and the communication module (4) is used for receiving the output signal of the gesture analysis module (3). The device and the method are convenient to use; and key input and coordinate positioning input can be obtained by moving both hands in a small movement range.

The present invention discloses a method and device for using azimuth gestures to remotely control smart home equipment; the method includes azimuth gesture remote control process, azimuth gesture classification and definition, remote control instruction classification and code, and the corresponding relationship between azimuth gestures and remote control instructions; The device includes a smart mobile terminal and a smart home device; the smart mobile terminal is used to remotely control the smart home device, and also includes a data acquisition module, a gesture analysis module, an instruction acquisition module, an instruction prompt module, an instruction confirmation module and an instruction sending module; The smart home device also includes an instruction receiving module and an instruction executing module; the orientation gestures include 3 kinds of click gestures, 8 kinds of sliding gestures, 8 kinds of long-press gestures after sliding, and 8 returning gestures after sliding; The 27 kinds of orientation gestures mentioned above replace the 27 buttons on the remote control. Users can even issue up to 27 remote control commands to the controlled smart home devices on the touch screen the size of a smart ring fingernail.

The invention relates to a robot tail end position and gesture analysis method. A transfer matrix between axes is expressed by four configuration parameters including the connecting rod lengths, the joint intersection angles, the connecting rod distances and the connecting rod intersection angles, and the gesture of the robot tail end relative to a reference coordinate system is expressed by rotation angles of three-time axis rotation. The method comprises the steps that the position and the gesture of the robot tail end relative to the reference coordinate system are derived by the use of the transfer matrix between the axes and the three-time axis rotation through the forward kinematics; the tail end predicted position and the tail end practical position are compared, and the speed correction quantity is calculated; the tail end expected speed is calculated by the use of an angular speed conversion matrix, the speed correction quantity is combined with the tail end expected speed, and then the tail end speed is obtained; the obtained speed of the robot tail end relative to the reference coordinate system is converted into angular speeds of joints by the use of the inverse kinematics; and the angular speeds of the joints are controlled within the maximum speed limit, and the angular speeds of the joints are combined with the current position, so that the rotation angles needed by the joints are obtained. The robot tail end position and gesture analysis method is simple in treatment process and can guarantee a certain accuracy.

The invention provides a gesture operating method, a gesture operating device and a mobile terminal. The gesture operating method comprises the steps of acquiring a gesture instruction; analyzing the gesture instruction into a plane characteristic of a projection plane and a vertical characteristic of a Z-axis direction, wherein the Z-axis is vertical to the projection plane; determining a target operational instruction which corresponds to the acquired gesture instruction according to the corresponding relation between the gesture instruction and the operational instruction; and performing the target operational instruction. According to the gesture operating method, the problem that man-machine interaction cannot be realized during a non-contact process in the prior art is solved. Furthermore, as the acquired gesture instruction is a three-dimensional gesture, analysis in the three-dimensional direction still can be kept in the process of analyzing the gesture instruction, the obtained gesture analysis result is more accurate, the gesture operating method is enabled to respond to more diversified gestures, and the response efficiency is higher and steadier.

The invention discloses a gesture interaction method and a terminal, and the gesture interaction method comprises the steps: photographing a gesture of a user through a camera in a one-time gesture interaction process, and obtaining an original image which comprises an RGB image; performing hand detection and gesture recognition on the RGB image by using a pre-trained deep neural network to obtaina first gesture recognition result; performing gesture analysis and confirmation based on the first gesture recognition result of each frame of RGB image in the multiple frames of RGB images to obtain a second gesture recognition result; triggering to execute an operation corresponding to the second gesture recognition result to complete gesture interaction. According to the embodiment of the invention, the gesture is detected and recognized by adopting the deep neural network, so that the probability of false detection and missing detection is reduced, the accuracy and robustness of gesturerecognition and gesture interaction are improved, and the user experience is improved.

The invention discloses a vehicle control system. A vehicle comprises a memory unit, a touch unit and an air conditioning system. The memory unit saves a corresponding relation table of preset gestures and action commands; the touch unit is used for responding to a touch gesture which is input by a user and generating an input signal. The vehicle control system comprises a gesture identification module, a gesture analysis module and a control module, wherein the gesture identification module is used for responding to the input signal, and detecting the touch gesture of the user according to the input signal; the gesture analysis module is used for comparing the touch gesture which is identified by the gesture identification module with the preset gestures which are saved in the corresponding relation table, and acquiring an action command corresponding to the preset gesture which is consistent with the touch gesture; when the touch gesture is the touch gesture that the touch unit slides in a first direction, the action command is to control the air conditioning system to raise the temperature in the vehicle; when the touch gesture is the touch gesture that the touch unit slides in a second direction, the action command is to control the air conditioning system to decrease the temperature in the vehicle; the control module is used for controlling the air conditioning system to increase or decrease the temperature in the vehicle.

The invention discloses a method and device for operating character input for an intelligent television by means of positional gestures. The method comprises following steps: positional gesture operation procedure, input page layout, character input rules and function calling rules. The device comprises an intelligent mobile terminal and an intelligent television; the intelligent mobile terminal is used for controlling character input for the intelligent television; the intelligent mobile terminal comprises a data acquisition module, a gesture analysis module, a command acquisition module, and a command sending module; the intelligent television comprises a command receiving module and a command execution module; the positional gestures comprise click gestures and sliding gestures; users use the positional gestures gesticulated on a touch screen of the intelligent mobile terminal to operate character input for intelligent televisions, intelligent glasses, intelligent helmets, and automobile central consoles; blind operation can be realized with user's eye sight being completely away from the intelligent mobile terminal touch screen; convenient and quick operation can be realized on small touch screens of smart watches and smart rings for users.

A method for providing adaptive gesture analysis may include dividing a distance range into a plurality of depth ranges, generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame, determining motion variation between the two image frames for each corresponding depth range, and determining depth of a target based at least in part on the motion variation. An apparatus and computer program product corresponding to the method are also provided.

A method for realizing the non-contact virtual mouse based on gesture recognition belongs to the technical field of human-computer interaction. In order to solve the problem of poor real-time performance of the existing non-contact human-computer interaction mode, the method comprises the following steps: obtaining video data stream by using a camera; intercepting the video stream and extracting frame images; separating a gesture from the video signal frame image; extracting model characteristic parameters for gesture analysis and recognition, classifying gestures according to model parametersand generating gesture descriptions according to specific needs; driving related application according to a mouse operation event. The method has the advantages of instantaneity and high efficiency,and can control the computer in non-contact state with gesture motion as input signal.

The invention discloses an orientation gesture input method and device for smart TVs or smart glasses; the method uses the orientation gestures made by the user's fingers on the touch screen of a handheld smart terminal to operate the Jiugong grid set on the screen of the smart TV or smart glasses The keyboard not only allows the user to quickly input on the touch screen as if using the cross-screen input method, but also keeps the user's eyes on the screen of the smart TV or smart glasses, thus realizing character input and Touch-blind operation of function call; the device includes hardware and software; the hardware includes a touch-type handheld smart terminal and a smart TV or smart glasses, and real-time data exchange is performed between the two through the transmission unit; The software includes a keyboard display module, a data acquisition module, a gesture analysis module, a function acquisition module, a character acquisition module, a function call module and a character input module.

The present invention discloses a method and device for using azimuth gesture to touch and operate a smart watch; the method includes azimuth gesture operation flow, button clicking rules, main page switching rules, and shortcut function calling rules; the device includes a smart ring, a Smart watch; the smart ring is provided with a touch screen; the touch screen is used to detect orientation gestures; the smart ring and the smart watch are installed with an application program; the application program includes a data acquisition module, a data sending module, and a data receiving module , a gesture analysis module, an instruction acquisition module, and an instruction execution module; the advantage of the present invention is that the user can operate the smart watch conveniently, accurately and quickly only by slightly moving the finger on the touch screen of the smart ring fingernail size; the user lifts the smart watch The action of the watch and the action of operating the smart watch are all done with the same hand; the user's fingers can perform blind operations on the touch screen of the smart ring.

The invention discloses a vehicle control system. A vehicle comprises a storage unit, a touch control unit and an audio presentation system, wherein a preset gesture and action command corresponding relation list is stored in the storage unit, and the touch control unit is used for responding to a touch control gesture input by a user and generating an input signal. The vehicle control system comprises a gesture identification module used for responding to the input signal and detecting the touch control gesture of the user according to the input signal, a gesture analysis module used for comparing the touch control gesture identified by the gesture identification module with a preset gesture stored in the corresponding relation list and acquiring an action command corresponding to the preset gesture consistent with the touch control gesture, and a control module used for controlling and regulating the volume of the audio presentation system; when the touch control gesture is a gesture sliding towards a first direction in the touch control unit, the action command is increasing the volume of the audio presentation system; when the touch control gesture is a gesture sliding towards a second direction in the touch control unit, the corresponding action command is lowering the volume of the audio presentation system.

The present invention discloses a method and device for operating the center console of a smart car by using an azimuth gesture; the method includes an azimuth gesture operation process, a button click rule, a main menu page switching rule, and an auxiliary function call rule; the device includes A sensor, a display screen, and a center console; the sensor is used to detect orientation gestures; the center console is installed with an application program; the application program includes a gesture analysis module, an instruction acquisition module, and an instruction execution module; the present invention Use the azimuth gesture of the driver's hand in the effective sensing space to operate the center console of the smart car in the air. Drivers can quickly grasp the orientation gestures after simple learning, and freely operate various functions of the center console of various smart cars; drivers can gesture orientation gestures only by intuition, without taking their eyes off the road ahead to ensure driving safety.

The invention discloses an RGBD depth sensor-based real-time gesture analysis and evaluation method and system. The real-time gesture analysis and evaluation system includes a static gesture recognition and evaluation system of a palm of a train driver and a dynamic gesture recognition and evaluation system of an arm of the train driver. The static gesture recognition and evaluation system of the palm of the train driver includes a palm centre position determination module, a palm region image extraction module, a denoising module and a gesture recognition and evaluation module. The dynamic gesture recognition and evaluation system of the arm of the train driver includes an arm skeleton node motion sequence extraction module, a dynamic gesture optimal-matching module and a dynamic gesture evaluation module of the arm. The real-time gesture analysis and evaluation system has very high robustness for environment backgrounds and illumination, adopts palm centre node-based gesture pixel searching when a palm gesture is detected, and improves a detection effect of the palm gesture; and the real-time gesture analysis and evaluation system supervises gestures of the driver in real time to ensure the safety of train driving, and can also avoid artificial monitoring on the gestures of the train driver, and reduce human resource consumption.

The invention discloses a virtual mouse control system, which runs in an electronic apparatus. The electronic apparatus comprises a touch display unit. The control system can control the electronic apparatus to display a virtual mouse and a cursor on the touch display unit. The control system comprises a gesture identification module, a gesture analysis module and a control module, wherein the gesture identification module is used for making a response to a touch signal and identifying a touch gesture according to the touch signal, the touch signal is generated in response to touch operation of the touch display unit, and the touch gesture includes a sliding gesture of dragging the virtual mouse on the touch display unit to slide and a clicking gesture of clicking the virtual mouse; the gesture analysis module is used for comparing the sliding gesture with a corresponding relationship table stored in a storage unit of the electronic apparatus, the corresponding relationship table stores a one-to-one correspondence relationship between a plurality of preset gestures and a plurality of action instructions, and each action instruction corresponds to a motion vector of the cursor; and the control module controls the cursor to move for a motion vector according to the action instruction corresponding to the preset gesture and enter an application or a link of a region in which the cursor is located.

The invention relates to the technical field of computer graphics and deep learning, and relates to a gesture recognition system, in particular to a three-dimensional gesture recognition system basedon a depth map. The three-dimensional gesture recognition system includes a camera, the camera is in signal connection with a depth sensor; the depth sensor is in signal connection with a data storagemodule; the data storage module is in signal connection with a data preprocessing module; the data preprocessing module is in signal connection with a segmentation module; the segmentation module isin signal connection with an input module; the distinguishing module is in signal connection with a static gesture analysis module and a dynamic gesture analysis module; the static gesture analysis module is in signal connection with a model construction module, the model construction module is in signal connection with a matching module, the matching module is in signal connection with a database, the dynamic gesture analysis module is in signal connection with a key point capture module, and the key point capture module is in signal connection with a function construction module. The systemhas the advantages that the reality sense is enhanced, and the man-machine interaction mode is enriched.