Nippon Telegraph and Telephone Corporation

Yoshihide Tonomura

Kota Hidaka

Takahiro Yamaguchi

Takayuki Nakachi

Yoko Ishii

Daisuke Shirai

Tetsuro Tokunaga

Yuichi Hiroi

Tatsuya Fujii

Masato Ono

Takahide Hoshide

Shinji Fukatsu

Hiromu Miyashita

Hidenobu Nagata

Masahiko Kitamura

Hirokazu Kakinuma

Jiro Nagao

A video generation device includes: an object extraction unit that extracts an object area from a captured video in a space; a spatial position tracking unit that detects an article from three-dimensional position measurement data in the space, applies identification information to the article, and calculates a three-dimensional spatial position of the article using the three-dimensional position measurement data; a position information merging unit that links the object area to the identification information of the article to associate the three-dimensional spatial position with the object area; a depth expression unit that generates a depth expression video of only the object area with which the three-dimensional spatial position has been associated, a depth of the video being able to be adjusted in the depth expression video; and a feedback unitthat transmits information indicating a method for reducing blurring generated in the object area of the depth expression video.

Video generation apparatus, method and program

A synchronous control system is provided. A transmission deviceincludes a reception unitthat receives a control signal for a lighting device in a live event site and a transmission unitthat transmits, to a reception device in a live viewing site, the control signal to which an output time is appended. The output time is obtained by adding a predetermined period of time to a receipt time at which the control signal is received. A reception deviceincludes a reception unitthat receives the control signal to which the output time is appended, and an output control unitthat outputs the control signal to a lighting devicein the live viewing site at the output time, and allows the control of the lighting deviceto synchronize with at least one of video and audio to be played in the live viewing site.

Synchronous control system, transmission device, reception device, synchronous control method, and synchronous control program

Accurate and rapid identification can be performed even when feature vectors of input pixels and background pixels are close. An image processing device includes: a feature extractor which extracts features of pixels from an input image and an input image of a different time; a quantization unit which reduces the number of gradations of features extracted by the feature extractor; a learning unitwhich learns combinations of the features of pixels through a machine learning algorithm that performs nonlinear identification and constructs a network according to machine learning; an LUT generatorwhich generates an LUT that replaces arithmetic operations of the network constructed by the learning unit; a foreground region estimatorwhich rapidly estimates similarity of each pixel of the input image to a foreground by referring to the LUT generated by the LUT generator; and a boundary correctorwhich classifies regions similar to the foreground estimated by the foreground region estimatorinto the foreground, a background, and an unclassified region including boundary pixels of the foreground and the background and performs boundary correction only on the unclassified region.

Video processing device, video processing method, and video processing program

To identify and track a plurality of objects. An object tracking deviceincludes a frame acquisition unitfor acquiring one set of frame dataincluded in moving image data that captures a space where a plurality of objects are present; a distance acquisition unitfor acquiring measurement datafrom measurement of three-dimensional coordinates of points configuring the objects in the space where the objects are present; an object position detection unitfor detecting a two-dimensional position of each of the objects from the frame dataon the basis of comparison with template data of each of the objects; an object distance detection unitfor detecting a plurality of three-dimensional positions of the objects from the measurement data; and an associating unitfor associating each two-dimensional position from the object position detection unitwith the nearest three-dimensional position among the three-dimensional positions from the object distance detection unit 34.

Object tracking device, object tracking method, and object tracking program

A selective PEG algorithm, creating a sparse matrix while maintaining row weight/column weight at arbitrary multi-levels, and in the process, inactivating an arbitrary edge so that a minimum loop formed between arbitrary nodes is enlarged or performing constrained interleaving, so that encoding efficiency in the case where a matrix space is narrow is improved.

Sparse graph creation device and sparse graph creation method

There is provided an object tracking apparatus that realizes robust object detection and tracking even for movement fluctuation and observation noise, an object tracking method and a computer program. An object cracking apparatusis an apparatus tracking an object in video, the object tracking apparatusincluding: a deep learning discriminatorwhich is a discriminator by deep learning; and a particle filter function unittracking an object by applying a multi-channel feature value of video including feature values by the deep learning discriminatorto likelihood evaluation by a particle filter, according to a distance between position information about the multi-channel feature value and position information about each particle.

Object tracker, object tracking method, and computer program

This method and device makes it possible to implement maximum likelihood decoding of a sparse graph code at low computational complexity in the maximum likelihood decoding of the sparse graph code. This is, in the maximum likelihood of decoding of the sparse graph code, a lost data decoding process by a trivial decoding method and a lost data decoding process by a Gauss elimination method are performed repeatedly and alternately.

Growing community of inventors

Musashino, Japan

Yoshihide Tonomura