Electronics and Telecommunications Research Institute

Korea Advanced Institute of Science and Technology

Sung Yong Shin

Junyong Noh

Jong Moo Sohn

Daseong Han

Ji Eun Kim

Dong Woo Lee

Min Gyu Choi

Hee Sook Shin

Chi Yoon Jeong

Moo Seop Kim

Yong Ki Son

Hyung Cheol Shin

Seokpyo Hong

Kyungmin Cho

Il Yeon Cho

Haegwang Eom

Bae Sun Kim

Ga Gue Kim

Hyung Sun Lee

Min Je Park

Chang Mok Oh

Gi Su Heo

A method of simulating a motion of an object controlling another object based on an example motion or a previously generated motion of the object is disclosed. The method includes refining a motion of a first object based on a motion of the first object predicted based on a motion specification, and on a trajectory of a second object controlled by the first object, and simulating the motion of the first object and the trajectory of the second object based on a vector for controlling joints of the first object that is generated based on the refined motion.

Method and apparatus for generating motion of object

Disclosed are a system and method for reproducing tactile content using spatial information, which enhances a users tactile sense of music by converting a sound of music played in a space into tactile sense in real time without any sense of difference between tactile and auditory sense and automatically correcting tactile information by reflecting a user location and spatial characteristics so that performance or image information may be realized as tactile content using spatial information and the user location.

System and method for reproducing tactile content using spatial information

Disclosed is a language learning technology for deaf people. A deaf-specific language learning system includes: a sound input device configured to receive a voice from an external source; a learning server configured to store learning data and correction information; a signal processor configured to output voice pattern information corresponding to a voice signal received from the sound input device; a learning processor configured to output learning pattern information regarding the learning data received from the learning server and also output a learning result through similarity analysis; and an actuator controller configured to vibrate a vibration actuator according to the voice pattern information and the learning pattern information.

Deaf-specific language learning system and method

Provided is a full-body modeling method and apparatus based on new model predictive control (MPC) with a visuomotor system in which visual perception and full-body motion control are integrated. The full-body modeling method includes determining a partial observation value associated with a state of an object based on a point of sight of a character, estimating the state of the object using the determined partial observation value based on a partially observable Markov decision process (POMDP), controlling a state of the character based on the estimated state of the object, and visualizing a motion of the character.

Full-body modeling method and apparatus based on model predictive control with visuomotor system

An electronic device capable of processing a user input without direct contact is disclosed. The electronic device according to an embodiment of the present disclosure may include a plurality of contact electrodes having one end thereof contacted with a user's body respectively to be electrically connected to the user's body, at least one body contact interface electrically connected to the plurality of contact electrodes through the user's body and having a predetermined impedance value, and a signal processing unit connected to other end of the plurality of contact electrodes respectively to form a circuit through the plurality of contact electrodes, the at least one body contact interface, and the user's body, and determining a user input corresponding to an impedance characteristic of the circuit.

Apparatus and method for determining user input of wearable electronic device using body contact interface

Technology for a method of detecting a user hand by a user hand detecting device. The method according to an aspect of the present invention includes extracting a first mask image from a depth image in which the user hand is imaged; extracting a second mask image having a preset skin color value among regions corresponding to the first mask image in a color image in which the user hand is imaged; generating a skin color value histogram model in a color space different from a region of the color image corresponding to a color region of the second mask image; generating a skin color probability image of the different color space from the color image using the skin color value histogram model and an algorithm for detecting a skin color region; and combining the skin color probability image with the second mask image and detecting the user's hand region.

User hand detecting device for detecting user's hand region and method thereof

A fabric type circuit board in which a conductive pattern is provided both faces of fabrics and a method of manufacturing the same. A fabric type circuit board includes fabrics and a conductive pattern in which extension units folded from one side of the fabrics to another side of the fabrics are formed, wherein the conductive pattern is formed using at least one of a copper film transfer printing scheme, printing, etching, embroidery, and sewing. A method of manufacturing a fabric type circuit board includes forming a conductive pattern, having extension units formed therein, on fabrics, cutting a part of the fabrics on which the conductive pattern is formed, and forming contact surfaces by folding the extension units from one side of the fabrics to another side of the fabrics.

Method of manufacturing a fabric type circuit board

Disclosed are a method and an apparatus for sensing touch input using illumination sensors. The apparatus includes: a touch pad on which at least one illumination sensor is arranged; and a controller collecting sensor values of the at least one illumination sensor to perform touch recognition suitable for a present illumination environment.

Method and apparatus for sensing touch input using illumination sensors

The present invention relates to the motion reconstruction method from inter-frame feature correspondences of a singular video stream using a motion library. The motion library is constructed through a motion capture system which is becoming more actively used or skilled animators. The present invention comprises the detailed information on the whole processes from images to motions. These processes are very simple to implement and straight forward. The total movement of a motion can be effectively inferenced and this technology can directly used for various fields in which human motions are produced from the images.

Growing community of inventors

Daejeon, South Korea

Sung Yong Shin