Abstract: A method of transferring a facial expression from a subject to a computer-generated character and a system and non-transitory computer-readable medium for the same. The method can include receiving an input image depicting a face of a subject; matching a first facial model to the input image; generating a displacement map representing of finer-scale details not present in the first facial model using a regression function that estimates the shape of the finer-scale details. The displacement map can be combined with the first facial model to create a second facial model that includes the finer-scale details, and the second facial model can be rendered, if desired, to create a computer-generated image of the face of the subject that includes the finer-scale details.

Abstract: A method of transferring a facial expression from a subject to a computer-generated character and a system and non-transitory computer-readable medium for the same. The method can include receiving an input image depicting a face of a subject; matching a first facial model to the input image; generating a displacement map representing of finer-scale details not present in the first facial model using a regression function that estimates the shape of the finer-scale details. The displacement map can be combined with the first facial model to create a second facial model that includes the finer-scale details, and the second facial model can be rendered, if desired, to create a computer-generated image of the face of the subject that includes the finer-scale details.

Abstract: A method of transferring a facial expression from a subject to a computer-generated character and a system and non-transitory computer-readable medium for the same. The method can include receiving an input image depicting a face of a subject; matching a first facial model to the input image; generating a displacement map representing of finer-scale details not present in the first facial model using a regression function that estimates the shape of the finer-scale details. The displacement map can be combined with the first facial model to create a second facial model that includes the finer-scale details, and the second facial model can be rendered, if desired, to create a computer-generated image of the face of the subject that includes the finer-scale details.

Abstract: A method and system for recognizing behavior is disclosed, the method includes: capturing at least one video stream of data on one or more subjects; extracting body skeleton data from the at least one video stream of data; computing feature extractions on the extracted body skeleton data to generate a plurality of 3 dimensional delta units for each frame of the extracted body skeleton data; generating a plurality of histogram sequences for each frame by projecting the plurality of 3 dimensional delta units for each frame to a spherical coordinate system having a plurality of spherical bins; generating an energy map for each of the plurality of histogram sequences by mapping the plurality of spherical bins versus time; applying a Histogram of Oriented Gradients (HOG) algorithm on the plurality of energy maps to generate a single column vector; and classifying the single column vector as a behavior and/or emotion.

Abstract: The present disclosure relates to a method, a device and a storage medium for implementing augmented reality. The method includes: obtaining a real scene, and according to shooting position and shooting direction of the real scene, obtaining POIs within a preset area and POI information corresponding to the POIs, the POI information comprising position information of the corresponding POI; creating a virtual plane, and mapping position relationship between the POIs on the virtual plane, and inserting tags of POI information to the location of the corresponding POI on the virtual plane; superimposing the virtual plane having the tags of POI information onto the real scene to form an augmented reality view; and displaying the augmented reality view, and adjusting the virtual plane according to real-time information of the real scene, to make the virtual plane be visually parallel to the horizontal plane of the real scene.

Abstract: The invention discloses a method for real-time face animation based on single video camera. The method tracks 3D locations of face feature points in real time by adopting a single video camera, and parameterizes head poses and facial expressions according to the 3D locations, finally may map these parameters into an avatar to drive face animation of an animation character. The present invention may achieve a real time speed by merely adopting a usual video camera of the user instead of an advanced acquisition equipment; the present invention may process all kinds of wide-angle rotations, translation and exaggerated expressions of faces accurately; the present invention may also work under different illumination and background environments, which include indoor and sunny outdoor.

Abstract: A method and system for recognizing behavior is disclosed, the method includes: capturing at least one video stream of data on one or more subjects; extracting body skeleton data from the at least one video stream of data; computing feature extractions on the extracted body skeleton data to generate a plurality of 3 dimensional delta units for each frame of the extracted body skeleton data; generating a plurality of histogram sequences for each frame by projecting the plurality of 3 dimensional delta units for each frame to a spherical coordinate system having a plurality of spherical bins; generating an energy map for each of the plurality of histogram sequences by mapping the plurality of spherical bins versus time; applying a Histogram of Oriented Gradients (HOG) algorithm on the plurality of energy maps to generate a single column vector; and classifying the single column vector as a behavior and/or emotion.

Abstract: The invention discloses a method for real-time face animation based on single video camera. The method tracks 3D locations of face feature points in real time by adopting a single video camera, and parameterizes head poses and facial expressions according to the 3D locations, finally may map these parameters into an avatar to drive face animation of an animation character. The present invention may achieve a real time speed by merely adopting a usual video camera of the user instead of an advanced acquisition equipment; the present invention may process all kinds of wide-angle rotations, translation and exaggerated expressions of faces accurately; the present invention may also work under different illumination and background environments, which include indoor and sunny outdoor.

Abstract: The present disclosure relates to a method, a device and a storage medium for implementing augmented reality. The method includes: obtaining a real scene, and according to shooting position and shooting direction of the real scene, obtaining POIs within a preset area and POI information corresponding to the POIs, the POI information comprising position information of the corresponding POI; creating a virtual plane, and mapping position relationship between the POIs on the virtual plane, and inserting tags of POI information to the location of the corresponding POI on the virtual plane; superimposing the virtual plane having the tags of POI information onto the real scene to form an augmented reality view; and displaying the augmented reality view, and adjusting the virtual plane according to real-time information of the real scene, to make the virtual plane be visually parallel to the horizontal plane of the real scene.

Abstract: A method of routing a voice call from a local media gateway to a terminating media gateway comprises determining IP network connectivity between the local media gateway and terminating media gateway and generating monitoring results, updating network resource status according to the monitoring results, generating a plurality of routes between the local media gateway and the terminating media gateway in response to the updated network resource status, determining a best route from the plurality of routes, and routing the voice call using the best route.

Abstract: A method of measuring network quality for VoIP calls comprises setting up a test call from a local IP endpoint to a remote IP endpoint reachable by a logical trunk group associated with the local IP endpoint, receiving statistical data regarding the test call, tearing down the test call, processing the statistical data and generating measurement results, and routing a VoIP call using a route selected based at least in part on the measurement results.

Abstract: A method, system, and computer-readable medium for selecting a route in a network are provided. A respective link cost is assigned to links of a plurality of routes, and a respective node cost is assigned to nodes of the plurality of routes. A respective link cost is calculated for each of the links, and a respective node cost is calculated for each of the nodes. A respective route cost for each of the plurality of routes is calculated based on the calculated link cost for each of the links and the calculated node cost for each of the nodes.

Abstract: A method, system, and computer-readable medium for selecting a route in a network are provided. A respective link cost is assigned to links of a plurality of routes, and a respective node cost is assigned to nodes of the plurality of routes. A respective link cost is calculated for each of the links, and a respective node cost is calculated for each of the nodes. A respective route cost for each of the plurality of routes is calculated based on the calculated link cost for each of the links and the calculated node cost for each of the nodes.

Abstract: A method of routing a voice call from a local media gateway to a terminating media gateway comprises determining IP network connectivity between the local media gateway and terminating media gateway and generating monitoring results, updating network resource status according to the monitoring results, generating a plurality of routes between the local media gateway and the terminating media gateway in response to the updated network resource status, determining a best route from the plurality of routes, and routing the voice call using the best route.

Abstract: A method of measuring network quality for VoIP calls comprises setting up a test call from a local IP endpoint to a remote IP endpoint reachable by a logical trunk group associated with the local IP endpoint, receiving statistical data regarding the test call, tearing down the test call, processing the statistical data and generating measurement results, and routing a VoIP call using a route selected based at least in part on the measurement results.