Nippon Telegraph and Telephone Corporation

Ken Tsutsuguchi

Noboru Sonehara

Yasuhiko Watanabe

Hitoshi Niigaki

Tetsuya Kinebuchi

Yasuhiro Yao

Masakatsu Aoki

Yasuhito Suenaga

A large-scale point cloud having no limitation on the range or the number of points is set as an object, and labels are attached to the points constituting the object regardless of the type of object. A three-dimensional point cloud label learning apparatusA includes a ground-based height calculation unit that receives a three-dimensional point cloud and a ground surface height as inputs and outputs a three-dimensional point cloud with a ground-based height, an intensity-RGB conversion unit that receives the three-dimensional point cloud with the ground-based height as an input and outputs an intensity-RGB converted three-dimensional point cloud with the ground-based height, a supervoxel clustering unit that receives the intensity-RGB converted three-dimensional point cloud with the ground-based height, a point cloud label for learning, and a clustering hyperparameter as inputs and outputs supervoxel data with a correct answer label, and a deep neural network learning unit that receives the supervoxel data with the correct answer label and a deep neural network hyperparameter as inputs and outputs a learned deep neural network parameter.

Three-dimensional point cloud label learning device, three-dimensional point cloud label estimating device, three-dimensional point cloud label learning method, three-dimensional point cloud label estimating method, and program

A digital contents editing method performs an editing operation of digital contents with a plurality of computers connected via a network. A digital contents editing apparatus or server accumulates the initial data of the digital contents and the editing operation information which is digitized, and transfers the editing operation information to clients which are involved in the editing operation. Each client then performs an editing operation of the digital contents by creating the editing operation information, in which the editing operation of the digital contents is digitized, and communicates only the editing operation information to other clients via the server and the network.

Digital contents editing method and apparatus thereof

The present invention offers a method for generating animations of a multi-articulated structure, a recording medium with the method recorded therein and an animation generating apparatus using the method. Motions of rigid sticks which approximate the upper arm connected to the shoulder joint and the lower arm connected by the elbow joint to the upper arm are modeled, by an interpolation scheme and/or equations of motion based on laws of physics, as temporal changes in angular positions in their respective constraint planes and the generated results are combined and output.

Method for generating animations of a multi-articulated structure,

Growing community of inventors

Tokyo, Japan

Ken Tsutsuguchi