647 results about "Motion recognition" patented technology

A method for controlling an electronic apparatus which uses voice recognition and motion recognition, and an electronic apparatus applying the same are provided. In a voice task mode, in which voice tasks are performed according to recognized voice commands, the electronic apparatus displays voice assistance information to assist in performing the voice tasks. In a motion task mode, in which motion tasks are performed according to recognized motion gestures, the electronic apparatus displays motion assistance information to aid in performing the motion tasks.

The invention discloses a remote control method for a television and a system for remotely controlling the television by same. The remote control method for the television is characterized by comprising the following steps: giving a specific gesture to a camera by an operator; transmitting the acquired specific gesture by the camera to a three-dimensional motion recognition module in the television for the three-dimensional motion and gesture recognition; acquiring three-dimensional motion coordinates of the specific gesture by the module, and outputting a control signal; executing corresponding programs according to the control signal by an executing device in the television. By utilizing the remote control method for the television, the remote control operation on the television can be performed by the gesture; and the remote control operation on the television becomes simpler and more humanized by means of a corresponding remote control operation system. In particular, the recreation functions which can be realized on a computer originally can be finished on the television without a mouse, a keyboard and other peripheral equipment of the computer based on the platform.

The invention discloses an image communication method and system based on facial expression/action recognition. In the image communication method based on facial expression recognition, firstly, an image is collected at the sending end, and the facial area in the image is determined; The facial expression feature parameters in the region are extracted; then the extracted facial expression feature parameters are sent to the receiving end; finally, the receiving end uses the facial expression feature parameters to control the local facial model of the receiving end to pass the The facial model reproduces the facial expression. The application of the present invention can not only enhance user experience, but also greatly reduce the requirement on the information transmission rate of the video bearer network, realize more effective video communication, and is especially suitable for wireless communication networks with limited network bandwidth and capacity.

A motion sensor-based user motion recognition method and portable terminal having a motion sensor is disclosed. The method recognizes user motions in a portable terminal. At least one parameter value is extracted from at least one user motion applied to the portable terminal. A reference parameter value serving as a user motion recognition reference is established according to at least one extracted parameter value. The established reference parameter value is stored.

The invention discloses a human body motion recognition method based on three-dimensional bone information. The method comprises the steps that color data stream, depth data stream and bone data stream of a number of individual samples of different sex and height are processed, wherein the individual samples make various motions; SVM models corresponding to all motions are constructed; the bone data stream of a recognized target which makes any motion within the acquisition range of a Kinect depth sensor is acquired; through the bone data stream, the distance between a normalized human body bone articulation point and a reference point and 14 vector angles are acquired; the data are respectively input to multiple SVM models; and a motion corresponding to the SVM model with the highest output probability is the motion of a recognition target. According to the invention, the Kinect depth sensor is used to acquire images; the method is less affected by light condition, shadow and other factors; the depth map and the bone information of a human body motion are acquired in real time; and a human body target in a scene can be accurately located.

Disclosed are an apparatus and a method for controlling music play in a mobile communication terminal. The apparatus includes a motion recognition sensor unit for detecting a motion of the mobile communication terminal and outputting detection signals, a sound source chip for outputting sound, and a controller for receiving the detection signals from the motion recognition sensor unit, calculating motion values of the mobile communication terminal, and controlling the sound source chip to output sounds dependent on the calculated motion values. The apparatus includes a user interface required for the music play, a display unit for displaying music to be played, a motion recognition sensor unit for detecting a motion of the mobile terminal, a sound file storage unit including an area for storing at least one music information, a controller for controlling corresponding music to be played according a motion of the mobile terminal, and a speaker for outputting sounds of the played music.

The invention discloses a motion recognition method based on a three-dimensional convolution depth neural network and depth video. In the invention, depth video is used as the object of study, a three-dimensional convolution depth neural network is constructed to automatically learn temporal and spatial characteristics of human body behaviors, and a Softmax classifier is used for the classification and recognition of human body behaviors. The proposed method by the invention can effectively extract the potential characteristics of human body behaviors, and can not only obtain good recognition results on an MSR-Action3D data set, but also obtain good recognition results on a UTKinect-Action3D data set.

An electronic apparatus and a method for controlling thereof are provided. The method recognizes one of among a user voice and a user motion through one of among a voice recognition module and a motion recognition module, and if a user voice is recognized through the voice recognition module, performs a voice task corresponding to the recognized user voice, and, if a user motion is recognized through the motion recognition module, performs a motion task corresponding to the recognized user motion.

Generating motion recognizers from example motions, without substantial programming, without limitation to any fixed set of well-known gestures, and without limitation to motions that occur substantially in a plane, or are substantially predefined in scope. From example motions for each class of motion to be recognized, a system automatically generates motion recognizers using machine learning techniques. Those motion recognizers can be incorporated into an end-user application, with the effect that when a user of the application supplies a motion, those motion recognizers will recognize the motion as an example of one of the known classes of motion. Motion recognizers can be incorporated into an end-user application; tuned to improve recognition rates for subsequent motions to allow end-users to add new example motions.

The invention discloses a deep learning-based human body motion recognition method of multi-channel image feature fusion. The method comprises: (1) extracting original RGB pictures from videos, and calculating dynamic graphs and optical flow graphs of the segmented videos through the RGB pictures; (2) carrying out cropping operations on the input pictures to expand a training data set; (3) constructing a three-channel convolutional-neural-network, and respectively inputting lastly obtained video segments into the three-channel convolutional-neural-network to carry out training to obtain a corresponding network model; and (4) for a to-be-recognized video segment, extracting original RGB pictures, calculating dynamic graphs and optical flow graphs corresponding thereto, and obtaining a recognition result of a final motion category. According to the method, the three-channel convolutional-neural-network is utilized for learning essential features of data for original input of different morphologies, multi-channel dense fusion operations are carried out on the data of the three morphologies in the middle of the network, expression ability of the features is improved, and purposes of multi-channel information sharing and a high accuracy degree are achieved.

A gesture recognition method comprises capturing images, processing the images to identify at least two clusters of touch points associated with at least two pointers, recognizing a gesture based on motion of the clusters, and updating a display in accordance with the recognized gesture.

There is provided a device for motion identification, the device comprising: an enclosure and a plurality of sensors being provided with the enclosure and configured to measure acceleration in three axes and angular motion in three axes. The acceleration may be measured in a first acceleration range and a second acceleration range,

The invention discloses a multi-modal action recognition method based on a depth neural network. The method comprehensively utilizes multi-modal information such as video images, optical flow diagramsand human skeleton. The specific steps are as follows: firstly, a series of preprocessing and compression are performed on the video; Obtaining an optical flow graph based on adjacent frames of the video; The human skeleton is obtained from the video frame by using the attitude estimation algorithm, and the path integral characteristics of the skeleton sequence are calculated. The obtained optical flow graph, skeleton path integration feature and original video image are input into a depth neural network with multi-branch structure to learn the abstract spatio-temporal representation of humanmotion and correctly judge its motion category. In addition, the pooling layer based on attention mechanism is connected to the video image branch, which enhances the abstract features closely related to the final motion classification results and reduces the irrelevant interference. The invention comprehensively utilizes multimodal information, and has the advantages of strong robustness and high recognition rate.

A motion recognition system and method for controlling electronic devices are disclosed, in which at least a micro inertial sensor, each being arranged at a specific location of a human body, is used to detect and measure a motion of the body so as to correspondently obtain a plurality of gesture parameters, such as angular velocity and acceleration, etc., and then the detected parameters are analyzed and converted into an input gesture sequence by a specific algorithm to be compared with a predefined motion information sequence so as to enable any of the controlled electronic devices to perform a specific operation according to the result of the comparison. In addition, a momentum can be obtained by performing a calculation upon the detected gestured parameters with respect to time, which can be used for controlling the interaction of the controlled electric devices.

Provided are a man-machine interaction method and man-machine interaction equipment based an acceleration sensor and motion recognition. The method includes the following steps: (1) a three-shaft acceleration sensor located on the man-machine interaction equipment collects X-axis acceleration data, Y-axis acceleration data and Z-axis acceleration data, and conveys the X-axis acceleration data, the Y-axis acceleration data and the Z-axis acceleration data to a controller of the man-machine interaction equipment; (2) the controller pre-processes the acceleration data, and removes noise and gravitational acceleration influences to obtain a precise X-axis acceleration sequence, a precise Y-axis acceleration sequence and a Z-axis acceleration sequence and to cache the acceleration sequences; (3) an acceleration threshold value is set, when the maximum of the X-axis acceleration sequence, the Y-axis acceleration sequence and the Z-axis acceleration sequence in cache is larger than the acceleration threshold value, the step (4) is carried out, and otherwise the step (1) is carried out; (4) motion mode recognition is carried out on the obtained X-axis acceleration sequence, the Y-axis acceleration sequence and the Z-axis acceleration sequence by means of a pre-trained classifier; (5) each motion mode corresponds to a trigger command, and the controller executes the corresponding trigger command according to a result after the motion mode recognition and provides corresponding feedback for a user; and (6) the steps from (1) to (5) are repeated.

[Problem to be Solved]

The present invention has an objective to improve operability in information input in an information processing device that includes a head mounted display to enable head tracking display.

[Solution]

An information processing device includes a hand-held operation unit (10), a head mounted display (20), a first motion sensor (506 to 508) that can detect at least the orientation of the head of the operator, and an information processing unit (30) that executes a head tracking displaying process in which the first motion sensor is used, and a specific process corresponding to an indication of the operator identified by the motion of the operation unit, wherein the motion of the operation unit is detected using a second motion sensor (1603 to 1605) incorporated in the operation unit.

The invention discloses a human body motion feature extraction method based on a global remarkable edge area, comprising steps of using a contrast between an area and a whole image to calculate the significance, reducing the color quantity of the color space, smoothing the significance of the color space, calculating the significance area according to the space relation of the neighboring areas, performing morphology gradient changing on the foreground area segmented by a binarized threshold to generate a global remarkable edge area, traversing strong corner points of all grids of the video frames under various sizes, collecting key characteristic points, the light stream amplitude value of which is not 0, in the remarkable edge area, solving the displacement of the strong corner point according to the corrected light stream field, and forming the human body motion local time space characteristic by using the strong corner point continuous multi-frame displacement locus and the neighbourhood gradient vector. The invention extracts the motion characteristics through global remarkable edge area, eliminates the background noise points irrelevant to the human body motion, removes the affect on the light stream calculation by the camera motion, improves the accuracy of the human body motion local time space characteristic description and improves the human body motion recognition rate.

The present invention relates to a motion recognition system for distinguishing motion between two different entity forms, such as distinguishing human motion from animal motion. The motion recognition system comprises a moving object detection component, a motion feature extraction component, and a motion feature classification component. The moving object detection component is configured to detect an object within a video sequence and generate a moving object signal. The motion feature extraction component is configured to receive the moving object signal and to extract features representing the detected object within the object signal. The motion feature classification component is configured to classify the features extracted from the detected object as either human motion or animal motion, thereby generating an identification signal. Through detecting, extracting and classifying the objection, a user can determine if the object is a human or an animal.