Electronics and Telecommunications Research Institute

The Industry & Academic Cooperation in Chungnam National University (iac)

Myongji University Industry and Academia Cooperation Foundation

Hee-Kyung Lee

Jin-Woo Hong

Jae-Gon Kim

Jin-Woong Kim

Jeong-Il Seo

Hui-Yong Kim

Jin-Soo Choi

Jung-Won Kang

Jin-Young Lee

Won-Sik Cheong

Hyon-Gon Choo

Gi-Mun Um

Han-Kyu Lee

Kyoung-Ro Yoon

Seung-Jun Yang

Dae-Young Song

Han-Shin Lim

Sun-Young Han

Dong-Hyeon Cho

Seong-Yong Lim

Disclosed herein are a method and apparatus for distributed image data processing. The method for distributed image data processing includes performing machine learning on an original image to produce a plurality of different task outputs, combining the plurality of task outputs to extract at least one final output, and compressing the final output and transmitting the final output to a server.

Method and apparatus for compression of a task output by machine learning

Disclosed herein are a method and apparatus for generating a panoramic image. The method includes configuring a data set for training a deep learning network based on K images, extracting an encoding feature map, a skip connection feature map, and a decoding feature map based on K/2 images, among the images, estimating multiple homographies based on the encoding feature map, estimating a flow adjustment map, a preprocessing blending map, a weight map, and a post-processing blending map based on the decoding feature map, deriving a flow map based on the multiple homographies and the flow adjustment map, generating a preprocessed image based on the preprocessing blending map, generating multiple warped images based on the preprocessed image and the flow map, generating a matching image based on the warped images and the weight map, and correcting the matching image based on the matching image and the post-processing blending map.

Method and apparatus for generating panoramic image based on deep learning network

Disclosed herein are an apparatus and method for 360-degree video stitching. The apparatus for 360-degree video stitching includes memory for storing at least one program, and a processor for executing the program, wherein the program is configured to stitch features of multiple input images based on at least one parameter included in a 360-degree stitching function description template, and then creating a single 360-degree video, the 360-degree stitching function description template includes a configuration parameter that is an array of function parameters, the configuration parameter includes a stitching parameter, a camera parameter, a feature parameter, and a projection parameter, the feature parameter includes a method for extracting respective features from multiple input images, and the projection parameter includes a projection type that is a kind of a projection plane onto which the multiple input images are projected.

Apparatus and method for 360-degree video stitching

Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a segmentation map. A feature vector for an image may be extracted using a segmentation map. The image may be encoded using the segmentation map and the feature vector. An output stream from an encoding apparatus may include a video stream and a feature stream. An input stream to a decoding apparatus may include a video stream and a feature stream. The image may be reconstructed using a reconstructed segmentation map and a reconstructed feature vector.

Method, apparatus and storage medium for image encoding/decoding using segmentation map

Provided are method and apparatus for generating a digital multimedia broadcasting application format. The apparatus includes: generating metadata for DMB contents; and combining the generated metadata and the DMB contents, wherein the metadata includes copyright information for the metadata, user information for a user who consumes the DMB contents, and package table information for describing a package related to the DMB contents.

Digital multimedia broadcasting application format generating method and apparatus thereof

Provided are an apparatus and method for providing an adaptive broadcast service for providing adaptive broadcasting contents including game contents to a user terminal of a home network environment by using game metadata, and an adaptive broadcasting system where a user or a terminal can properly select and consume a game based on the object by defining the metadata for describing the common characteristic of the predetermined contents type including the game and the metadata for describing the characteristic of only the game contents. The apparatus includes: a contents providing unit for publishing and providing the adaptive broadcasting contents including the game contents, and the game metadata to the user terminal; and a contents searching unit for providing contents identification information corresponding to a search and selection signal transmitted from the user terminal, wherein the game metadata describe characteristics of the game contents.

Apparatus and method for providing adaptive broadcast service using game metadata

The present research relates to description supporting a targeting scheme, more particularly, to an extended description structure supporting a targeting scheme and a TV-Anytime service providing method and system employing the same based on Moving Picture Experts Group 21 (MPEG-21) Usage Environment Description (UED) tools. The TV-Anytime service providing system employing the extended description structure includes a service providing apparatus for generating package metadata including user information and usage environment information; and a user device for acquiring the package metadata including user information and usage environment information from the service providing apparatus through diverse access networks.

Extended description to support targeting scheme, and TV anytime service and system employing the same

Growing community of inventors

Daejeon, South Korea

Hee-Kyung Lee