Abstract: A machine learning system determines whether an influence which exclusion and addition of evaluation target data from and to learning data has on the performance of a machine learning model includes: an acquisition unit that acquires an initial data group used to learn a learning model, evaluation target data added to, or excluded from, the initial data group, and a verification data group including at least one element which is not included in the evaluation target data; and a contribution degree calculation unit that calculates a contribution degree for evaluating an influence which the evaluation target data has on performance of the learning model, on the basis of an output value by the learning model for which the verification data group is input, and an output value by a relearning model which is learned by adding or excluding the evaluation target data to or from the initial data group.

Abstract: A computer, which is configured to generate learning data for use in machine learning for generating model information to be set to a system that is configured to generate second output data from first output data, the first output data being generated by processing input data with use of the model information, the computer being configured to: obtain analysis input data; generate, from the analysis input data, first to-be-analyzed output data based on an arbitrary generation condition; generate second to-be-analyzed output data from the first to-be-analyzed output data; analyze the second to-be-analyzed output data; and generate, as the learning data, data including the analysis input data and the first to-be-analyzed output data in a case where the second to-be-analyzed output data fulfills a user's demand.

Abstract: A video display system performs a video conversion process on a video of a camera mounted on a vehicle and displays a resulting video, and includes a plurality of cameras, a detecting unit that detects an object of interest around the vehicle based on information or the like acquired through the plurality of cameras, other sensors, or a network, a transforming/synthesizing unit that transforms and synthesizes the videos photographed by the plurality of cameras using a shape of a virtual projection plane, a virtual viewpoint, and a synthesis method which are decided according to position information of the object of interest detected by the detecting unit, and a display unit that displays the video that is transformed and synthesized by the transforming/synthesizing unit.

Abstract: A video display system performs a video conversion process on a video of a camera mounted on a vehicle and displays a resulting video, and includes a plurality of cameras, a detecting unit that detects an object of interest around the vehicle based on information or the like acquired through the plurality of cameras, other sensors, or a network, a transforming/synthesizing unit that transforms and synthesizes the videos photographed by the plurality of cameras using a shape of a virtual projection plane, a virtual viewpoint, and a synthesis method which are decided according to position information of the object of interest detected by the detecting unit, and a display unit that displays the video that is transformed and synthesized by the transforming/synthesizing unit.

Abstract: A technique to output map information to appropriately match imaged images is to be provided. An information processing device includes an input unit that inputs image information acquired by imaging; an output unit that outputs map information; and a control unit that controls the input unit and the output unit, wherein the control unit performs control, according to depth distance information acquired from the image information, to vary the downscale ratio of the map information outputted from the output unit.

Abstract: There is provided a video processing apparatus comprising a motion vector detection unit for detecting data on the motions of objects by using at least two frames, an interpolation frame generation unit for generating interpolation frames in the horizontal/vertical and temporal directions in accordance with the motion vectors obtained by the motion vector detection unit, and an image feature detection unit for detecting the features of motions extended over the at least two frames, wherein the procedures, performed by the image feature detection unit, of generating interpolation frames in the horizontal/vertical and temporal directions are switched over in accordance with the features of motions.

Abstract: For smoothing motion of an video during time of a special reproduction, in a video reproducing apparatus, for outputting an input video signal while holding it temporarily therein, comprises a buffering portion (100), and a video speed converter portion (101), for producing an interpolation frame responding to motion of video with using a plural number of video frames, which are outputted from the buffering portion, and thereby outputting a video signal, a reproduction speed of which is converted by combining the interpolation frame and the video frame from the buffering portion. And, a time distance of video frames of the video signal, which is outputted from the buffering portion, as well as, a producing process and a combining process, for producing an interpolation frame within the video speed converter portion, are controlled depending on a control signal indicating a reproduction speed.

Abstract: A motion vector detection apparatus is disclosed capable of detecting accurate motion vectors from between a previous frame of image and the presently displayed frame of image even in edge regions of the frames where inaccurate motion vectors would normally tend to be detected. A motion vector-detecting portion reads in an image signal from the signal input portion as well as image signals entered through first through third frame memories. Processing for detecting motion vectors is performed, based on four frames entered in synchronism to the motion vector-detecting portion out of the frames forming the image signals. Vectors produced between the image signal from the first frame memory delayed by one frame relative to the image signal from the signal input portion and the image signal from the second frame memory delayed by two frames relative to the image signal from the signal input portion are detected as motion vectors.

Abstract: There is provided a video processing apparatus comprising a motion vector detection unit for detecting data on the motions of objects by using at least two frames, an interpolation frame generation unit for generating interpolation frames in the horizontal/vertical and temporal directions in accordance with the motion vectors obtained by the motion vector detection unit, and an image feature detection unit for detecting the features of motions extended over the at least two frames, wherein the procedures, performed by the image feature detection unit, of generating interpolation frames in the horizontal/vertical and temporal directions are switched over in accordance with the features of motions.

Abstract: A moving object measuring apparatus includes: a movement trajectory information acquisition portion that obtains movement trajectory information indicating a movement trajectory of a moving object from images included in two or more video sequences that are stored, for each of the two or more video sequences separately; a three-dimensional trajectory information acquisition portion that obtains three-dimensional trajectory information that is information of a three-dimensional trajectory of the moving object by using Visual Hulls Method, based on the movement trajectory information obtained by the movement trajectory information acquisition portion for each of the two or more video sequences separately and two or more camera parameters that are stored; and a three-dimensional trajectory information output portion that outputs the three-dimensional trajectory information.