Electronics and Telecommunications Research Institute

University-Industry Cooperation Group of Kyung Hee University

The Industry & Academic Cooperation in Chungnam National University

Gi Mun Um

Won Sik Cheong

Nam Ho Hur

Gun Bang

Gwang Hoon Park

Kyung Yong Kim

Hong Chang Shin

Il Gu Jung

Hee Kyung Lee

Kwang Yong Kim

Yoo Kyung Kim

Hyun Jae Lee

Won Geun Ryu

Jeong Il Seo

Chan Soo Kim

Kee Seong Cho

Sang Joon Park

Chang Eun Lee

Seong Yong Lim

Eun Young Chang

Eung Don Lee

Tae One Kim

Joung Il Yun

Dae-Young Song

Donghyeon Cho

Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.

Image encoding method using a skip mode, and a device using the method

A deep learning-based image stitching method and apparatus are provided. The deep learning-based image stitching method includes receiving a plurality of images including a first image and a second image stitched to the first image, extracting a feature map of the plurality of images, generating a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map, generating a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively, generating a plurality of weight maps for blending the plurality of warping images, based on the feature map, and generating a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps.

Deep learning-based image stitching method and apparatus

Disclosed herein is a method of creating an image stitching workflow including acquiring 360-degree virtual reality (VR) image parameters necessary to makes a request for image stitching and create the image stitching workflow, acquiring a list of functions applicable to the image stitching workflow, creating the image stitching workflow based on functions selected from the list of functions, determining the number of media processing entities necessary to perform tasks configuring the image stitching workflow and generating a plurality of media processing entities according to the determined number of media processing entities, and allocating the tasks configuring the image stitching workflow to the plurality of media processing entities.

Method and apparatus for providing 360 stitching workflow and parameter

The present invention relates to a method and apparatus for performing object segmentation in an image. More particularly, the present invention divides a screen of an input image into at least two sub-images, and generates one image by combining the at least two sub-images to which an image segmentation algorithm is respectively applied.

Method and apparatus for performing segmentation of small objects within moving pictures in real-time

Provided are an apparatus and method for generating a best-view image centered on a object of interest in multiple camera images. The apparatus and method for generating a best-view image centered on a object of interest in multiple camera images accurately provide a best-view image clearly showing a figure, a motion, or the like of a object of interest desired by a viewer by selecting the best-view camera image on the basis of a criterion of a judgment about the best-view image centered on the object of interest.

Apparatus and method for generating best-view image centered on object of interest in multiple camera images

A multi-camera control apparatus and method to maintain a location and a size of an object in a continuous viewpoint switching service are provided. The multi-camera control method of controlling a main camera configured to capture a moving object of interest and controlling at least one sub-camera configured to capture the object of interest at a different viewpoint from that of the main camera, may include extracting the object of interest from a first image generated by the main camera, controlling a capturing scheme of the main camera based on a change in a location and a size of the extracted object of interest, projecting the object of interest onto a second image generated by the sub-camera, and controlling a capturing scheme of the sub-camera based on a change in a location and a size of the projected object of interest.

Multi-camera control apparatus and method to maintain location and size of object in continuous viewpoint switching service

Provided are an image magnification apparatus and method for three-dimensional display images. A multi-view image magnification apparatus includes: a region designation detection unit for detecting detection regions corresponding to the magnification regions of three-dimensional display images from original view images; a magnification ratio determination unit for determining the magnification ratios of the magnification regions; and a partial multiplexing unit for multiplexing non-detection regions except for the detection regions of the original view images according to a predetermined resolution and multiplexing the detection regions according the resolution which is different from the resolution of the non-detection regions on the basis of the magnification ratios. The present invention can magnify the images without lowering the resolution in a three-dimensional display.

Apparatus and method for encoding/decoding multi-view images

Provided are an apparatus and a method for generating a multi-viewpoint image. The apparatus includes: a camera photographing a stereo image; an image processing unit detecting features from left and right images of the stereo image; a reference image generating unit generating a reference image for viewpoint n by warping an image which is distant between the left image and the right image at viewpoint n based on an n-th viewpoint among N viewpoints that exist between the left image and the right image; and a warping image generating unit calculating a warping equation for viewpoint n by using the reference image and generating a final warping image for viewpoint n by using the calculated warping equation.

Apparatus and method for generating multi-viewpoint image

There are provided a method and apparatus for controlling an electronic device. The apparatus for controlling an electronic device includes a marker recognition unit configured to recognize the marker of the electronic device and a control unit configured to perform communication with the electronic device based on the marker and control the electronic device using a Graphic User Interface (GUI) program received from the electronic device.

Method and apparatus for controlling electronic device

Growing community of inventors

Daejeon-si, South Korea

Gi Mun Um