Abstract: A human-computer interaction method and apparatus. Said method may include: receiving information of at least one modality of a user (201); identifying, on the basis of the information of the at least one modality, intention information of the user and user emotional features corresponding to the intention information (202); determining, on the basis of the intention information, reply information to the user (203); selecting, on the basis of the user emotional features, character emotional features to be fed back to the user (204); and generating, on the basis of the character emotional features and the reply information, a broadcast video of an animated character corresponding to the character emotional features (205).

Abstract: A disappearing direction determination device and method, a video camera calibration apparatus and method, a video camera and a computer program product are provided. The device comprises: a moving target detecting unit for detecting in the video image a moving target area where a moving object locates; a feature point extracting unit for extracting at least one feature point on the moving object in the detected moving target area; a moving trajectory obtaining unit for tracking a movement of the feature point in a predetermined number of video image frames to obtain a movement trajectory of the feature point; and a disappearing direction determining unit for determining, according to the movement trajectories of one or more moving objects in the video image, a disappearing direction pointed by a major moving direction of the moving objects. Thus, a disappearing direction and video camera gesture parameters can be determined accurately.

Abstract: A disappearing direction determination device and method, a video camera calibration apparatus and method, a video camera and a computer program product are provided. The device comprises: a moving target detecting unit for detecting in the video image a moving target area where a moving object locates; a feature point extracting unit for extracting at least one feature point on the moving object in the detected moving target area; a moving trajectory obtaining unit for tracking a movement of the feature point in a predetermined number of video image frames to obtain a movement trajectory of the feature point; and a disappearing direction determining unit for determining, according to the movement trajectories of one or more moving objects in the video image, a disappearing direction pointed by a major moving direction of the moving objects. Thus, a disappearing direction and video camera gesture parameters can be determined accurately.

Abstract: A disappearing direction determination device and method, a video camera calibration apparatus and method, a video camera and a computer program product are provided. The device comprises: a moving target detecting unit for detecting in the video image a moving target area where a moving object locates; a feature point extracting unit for extracting at least one feature point on the moving object in the detected moving target area; a moving trajectory obtaining unit for tracking a movement of the feature point in a predetermined number of video image frames to obtain a movement trajectory of the feature point; and a disappearing direction determining unit for determining, according to the movement trajectories of one or more moving objects in the video image, a disappearing direction pointed by a major moving direction of the moving objects. Thus, a disappearing direction and video camera gesture parameters can be determined accurately.

Abstract: The present invention relates to a method and apparatus for extracting key frames from a video. The method includes: dividing the video into multiple levels of video segments, wherein each video segment at a non-lowest level comprises one or more video segments at the next lower level, the multiple levels range from a first level to an N-th level, N is an integer greater than 1, the first level is the lowest level, and the N-th level is the highest level; extracting from video segments of the video at a non-highest level candidate frames at the non-highest level; for each level from a next higher level to the highest level, selecting zero, one or more candidate frames at the level from candidate frames at the next lower level in each video segment at the level; and outputting the candidate frames at the highest level as the key frames of the video.

Abstract: A motion capture apparatus includes: generating means; predicting means; projecting means; evaluating means; and estimating means. The generating means generates a kinematics model having joints connected to one another. The predicting means hierarchically calculates predicted positions at a current time of the joints of the objective person, and predicts three-dimensional positions and postures of the joints and the limbs. The projecting means projects the three-dimensional positions and postures of the joints and the limbs of the objective person on a two-dimensional image plane, the three-dimensional positions and the postures being predicted by predicting means. The evaluating means evaluates reliability about projection positions projected by the projecting means based on the observation image of the objective person.

Abstract: A disappearing direction determination device and method, a video camera calibration apparatus and method, a video camera and a computer program product are provided. The device comprises: a moving target detecting unit for detecting in the video image a moving target area where a moving object locates; a feature point extracting unit for extracting at least one feature point on the moving object in the detected moving target area; a moving trajectory obtaining unit for tracking a movement of the feature point in a predetermined number of video image frames to obtain a movement trajectory of the feature point; and a disappearing direction determining unit for determining, according to the movement trajectories of one or more moving objects in the video image, a disappearing direction pointed by a major moving direction of the moving objects. Thus, a disappearing direction and video camera gesture parameters can be determined accurately.

Abstract: An image processing apparatus includes: an image pyramid forming section configured to form an image pyramid by hierarchically creating layered image data including differently scaled images from inputted image data; a position calculating section configured to determine an in-image-pyramid position as a height position in the image pyramid to which template image data having an image portion of a target object at a fixed scale corresponds; an upper-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between upper-side layer image data directly above the in-image-pyramid position, and a state prediction; a lower-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between lower-side layer image data directly below the in-image-pyramid position, and a state prediction; and a true likelihood calculating section configured to determine a true likelihood from the likelihoods determined by the upper

Abstract: The present invention relates to a method and apparatus for extracting key frames from a video. The method includes: dividing the video into multiple levels of video segments, wherein each video segment at a non-lowest level comprises one or more video segments at the next lower level, the multiple levels range from a first level to an N-th level, N is an integer greater than 1, the first level is the lowest level, and the N-th level is the highest level; extracting from video segments of the video at a non-highest level candidate frames at the non-highest level; for each level from a next higher level to the highest level, selecting zero, one or more candidate frames at the level from candidate frames at the next lower level in each video segment at the level; and outputting the candidate frames at the highest level as the key frames of the video.

Abstract: An image processing device that models, based on a plurality of frame images being results of time-sequential imaging of an object in motion, a motion of the object using a three-dimensional (3D) body configured by a plurality of parts is disclosed. The device includes: acquisition means for acquiring the frame images being the imaging results; estimation means for computing a first matrix of coordinates of a joint of the 3D body and a second matrix of coordinates of each of the parts of the 3D body, and generating a first motion vector; computing means for computing a second motion vector; and determination means for determining the 3D body.

Abstract: An image processing apparatus includes: an image pyramid forming section configured to form an image pyramid by hierarchically creating layered image data including differently scaled images from inputted image data; a position calculating section configured to determine an in-image-pyramid position as a height position in the image pyramid to which template image data having an image portion of a target object at a fixed scale corresponds; an upper-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between upper-side layer image data directly above the in-image-pyramid position, and a state prediction; a lower-layer-side likelihood calculating section configured to determine a likelihood for a target object by matching between lower-side layer image data directly below the in-image-pyramid position, and a state prediction; and a true likelihood calculating section configured to determine a true likelihood from the likelihoods determined by the upper

Abstract: A dynamic-state estimating apparatus includes a control-point setting unit setting a plurality of control points for a three-dimensional object model; a control-point color-information acquiring unit acquiring control-point color information indicating the color at a projection position where each control point is projected on an object image; an initial control-point color-information storing unit storing the control-point color information acquired from the object image for initial setup as initial control-point color information; a control-point position estimating unit estimating the position of each control point at a current time; a current control-point color-information acquiring unit acquiring current control-point color information resulting from projection of the control point on the object image at the current time; and a likelihood calculating unit calculating a likelihood by using the current control-point color information and the initial control-point color information.

Abstract: An image processing method and apparatus is disclosed which can produce parallax data between a plurality of image data with a high degree of accuracy. Probability density functions are updated successively, and a corresponding relationship which minimizes the energy in each of the probability density functions is specified. Then, that one of the probability density functions which finally minimizes the energy and parallax data corresponding to the correspondence relationship are specified.

Abstract: A tracking processing apparatus includes: first state-variable-sample-candidate generating means for generating state variable sample candidates at first present time; plural detecting means each for performing detection concerning a predetermined detection target related to a tracking target; sub-information generating means for generating sub-state variable probability distribution information at present time; second state-variable-sample-candidate generating means for generating state variable sample candidates at second present time; a state-variable-sample acquiring means for selecting state variable samples out of the state variable sample candidates at the first present time and the state variable sample candidates at the second present time at random according to a predetermined selection ratio set in advance; and estimation-result generating means for generating main state variable probability distribution information at the present time as an estimation result.

Abstract: An image processing device that models, based on a plurality of frame images being results of time-sequential imaging of an object in motion, a motion of the object using a three-dimensional (3D) body configured by a plurality of parts is disclosed. The device includes: acquisition means for acquiring the frame images being the imaging results; estimation means for computing a first matrix of coordinates of a joint of the 3D body and a second matrix of coordinates of each of the parts of the 3D body, and generating a first motion vector; computing means for computing a second motion vector; and determination means for determining the 3D body.

Abstract: A motion capture apparatus includes: generating means; predicting means; projecting means; evaluating means; and estimating means. The generating means generates a kinematics model having joints connected to one another. The predicting means hierarchically calculates predicted positions at a current time of the joints of the objective person, and predicts three-dimensional positions and postures of the joints and the limbs. The projecting means projects the three-dimensional positions and postures of the joints and the limbs of the objective person on a two-dimensional image plane, the three-dimensional positions and the postures being predicted by predicting means. The evaluating means evaluates reliability about projection positions projected by the projecting means based on the observation image of the objective person.

Abstract: An image processing method and apparatus is disclosed which can produce parallax data between a plurality of image data with a high degree of accuracy. Probability density functions are updated successively, and a corresponding relationship which minimizes the energy in each of the probability density functions is specified. Then, that one of the probability density functions which finally minimizes the energy and parallax data corresponding to the correspondence relationship are specified.