Korea Electronics Technology Institute

Samsung Electronics Co., Ltd.

Je Woo Kim

Byeong Ho Choi

Hwa Seon Shin

Ji Ho Park

Yong Hwan Kim

Choong Sang Cho

Dong Sun Kim

Ju Hong Yoon

Min Gyu Park

Byeng Ho Choi

Jae-Gon Kim

Joon Ki Paik

Yo Sung Ho

Kwang Hoon Sohn

Cheon Lee

Hyok Song

Charles Hyok Song

Young Jun Hwang

Seung Yerl Lee

Ju Mi Kang

Dong Il Park

Yong Hoon Kwon

Jeong Eun Lim

Sang Seol Lee

Hyeok Koo Jung

Jin Su Myung

Joo Young Yi

Doo San Baek

Soon Young Yoon

Jae Heung Yeom

There are provided an apparatus and a method for reconstructing a 3D human object in real time based on a monocular color image. A 3D human object reconstruction apparatus according to an embodiment extracts a pixel-aligned feature from a monocular image, extracts a ray-invariant feature from the pixel-aligned feature, generates encoded position information by encoding position information of a point, predicts a SD of a point from the ray-invariant feature and the encoded position information which are extracted, and reconstructs a 3D human object by using the predicted SD. Accordingly, the ray-invariant feature extracted from the pixel-aligned feature, and the encoded position information are used, so that an amount of computation for predicting SDs of points of a 3D space can be noticeably reduced and a speed can be remarkably enhanced.

Real-time 3D human object reconstruction apparatus and method based on monocular color image

A method and an apparatus for detecting a lane is provided. The lane detection apparatus according to an embodiment includes: an acquisition unit configured to acquire a front image of a vehicle; and a processor configured to input the image acquired through the acquisition unit to an AI model, and to detect information of a lane on a road, and the AI model is trained to detect lane information that is expressed in a plane form from an input image. Accordingly, data imbalance between a lane area and a non-lane area can be solved by using the AI model which learns/predicts lane information that is expressed in a plane form, not in a segment form such as a straight line or curved line.

Image-based lane detection and ego-lane recognition method and apparatus

The present invention relates to a method for transmitting and receiving program configuration information for a scalable ultra high definition (UHD) video service under the hybrid transmission environment, and to a method and apparatus for effectively transmitting scalar layer information, and more particularly, the present invention relates to a scheme for inserting group information for the scalable layer of a base layer and an enhancement layer, which form a scalable UHD video, and transmission channel information into a program map table (PMT) or a package configuration table (PCT), and for transmitting same, and to a scalable layer information format for transmitting layer information with a smaller number of bits as possible when a packet header includes scalable layer information.

Method for transmitting and receiving program configuration information for scalable ultra high definition video service in hybrid transmission environment, and method and apparatus for effectively transmitting scalar layer information

The present invention relates to an input/output system for an ultra high definition image, and more specifically, to an input/output system for an ultra high definition image that may receive an ultra high definition image signal from an external device, process the signal in real time, and output the processed ultra high definition image signal. For this purpose, a system configured to convert data having various resolutions into UHD data of the present invention includes a content input/output device configured to provide data received from a data providing device to an editing device and provide the data received from the editing device to a content reproducing device, and an editing device configured to convert the data received from the content input/output device into UHD data and provide the result to the content input/output device.

Input/output system for editing and playing ultra-high definition image

A method for separating audio sources and an audio system using the same are provided. The method introduces the concept of a residual signal to separate a mixed audio signal into audio sources, and separates an audio signal corresponding to at least two of the audio sources as a residual signal and processes the audio signal separately. Therefore, audio separation performance can be improved. In addition, the method re-separates a separated residual signal and adds the separated residual signals to corresponding audio sources. Therefore, audio sources can be separated more safely.

Method for separating audio sources and audio system using the same

A calibration system for stereo cameras includes a rig control module configured to, when a camera calibration parameter is input, control an auto rig according to the camera calibration parameter to perform physical calibration for a camera, a stereo image calibration apparatus configured to calibrate a stereo image to acquire the camera calibration parameter, and output the acquired camera calibration parameter, and a camera control module configured to output the camera calibration parameter, which is input from the stereo image calibration apparatus, to the rig control module, or screen-output the camera calibration parameter. Therefore, physical calibration and image processing calibration for a camera are performed in association with each other.

Calibration system for stereo camera and calibration apparatus for calibrating stereo image

The present invention relates to a method for selecting an appropriate mode when performing a new broadcast, such as a 3D stereo broadcast, a UHDTV broadcast, and a multi-view broadcast, among others, while maintaining compatibility with existing broadcasting channels in an MPEG-2-TS format for transmitting and receiving digital TV, and to a method for recognizing a descriptor. To this end, the present invention suggests providing the descriptor which is related to synthesizing left and right images using the type of stream, existence of the descriptor, and a frame-compatible mode flag.

Method for providing and recognizing transmission mode in digital broadcasting

Provided are an apparatus and a method for encoding a high fidelity video, and an apparatus and a method for decoding a high fidelity video. A video encoding method for encoding first to third planes having different color components includes performing intra prediction in the first plane or inter prediction between each frame for a block of the first plane, and generating a first residue corresponding to a difference between the block of the first plane and the predicted block of the first plane, predicting a block of the second plane using a reconstructed pixel peripheral to the block of the second plane and a reconstructed pixel peripheral to the block of the first plane corresponding to the reconstructed pixel peripheral to the block of the second plane, and generating a second residue corresponding to a difference between the block of the second plane and the predicted block of the second plane, predicting a block of the third plane using a reconstructed pixel peripheral to the block of the third plane and any one of a reconstructed pixel peripheral to the block of the first plane corresponding to the reconstructed pixel peripheral to the block of the third plane and a reconstructed pixel peripheral to the block of the second plane corresponding to the reconstructed pixel peripheral to the block of the third plane, and generating a third residue corresponding to a difference between the block of the third plane and the predicted block of the third plane, and encoding the first to third residues.

Apparatus and method for encoding and decoding high fidelity video, and computer-readable storage medium

Disclosed is an apparatus for playing and producing realistic object audio. The apparatus for playing realistic object audio includes: a deformatter unit individually separating scene description (SD) compression data and object audio compression data from inputted audio files; an SD decoding unit decoding the SD compression data to restore SD information; an object audio decoding unit decoding the object audio compression data to restore object audio signals which are respective audio signals of a plurality of objects; and an object audio effect unit adding an audio effect for each object to the object audio signals according to SD information for each object corresponding to the object audio signals among the SD information to produce a realistic object audio signal corresponding to each of the object audio signals.

Apparatus for playing and producing realistic object audio

In a method for image prediction of a multi-view video codec, a disparity vector value of a current macroblock is obtained and a corresponding macroblock is searched through the obtained disparity vector value. An intra prediction coding direction value of the searched macroblock is determined as an intra prediction coding direction value of the current macroblock. The current macroblock is coded/decoded through the determined intra prediction coding direction value. The coding efficiency can be increased by reducing a coding amount by omitting a process of obtaining an unnecessary disparity value by using a different-view intra prediction coding direction as a current-view intra prediction coding direction. The coding efficiency can be increased by reducing a coding amount by differentially coding a similar disparity vector. The reliability can be increased through an accurate disparity using multiples of 8 rather than 16, in motion skip for sharing the format of a macroblock.

Method for image prediction of multi-view video codec and computer-readable recording medium thereof

The present invention provides a new recursive FIR filter scheme which supports a variable order short-term predictor, and uses a pipeline stall based on the radix-2 algorithm and an autocorrelation processing time for reducing the complexity of MPEG-4 ALS hardware implementation.

Variable order short-term predictor

A lossless image compression method for a high definition image is provided. The image compression method generates a minimum value of values produced by subtracting a current virtual pixel value from an average of neighbor pixels designated by a plurality of directions, as the prediction value of a current pixel. Thus, the image compression more efficient than the current JPEG-LS can be achieved.

Lossless image compression and decompression method for high definition image and electronic device using the same

An image encoding method using color space estimation is provided. A method for encoding a second color space pixel corresponding to coordinates of a first color space pixel using color spaces, includes encoding a pixel of a first color space; calculating a color space estimation value of a current pixel of a second color space by referring to the encoded pixel of the first color space; and encoding a differential value of the calculated color space estimation value and the current pixel value. Thus, the image compression efficiency can be enhanced by using the information between the color spaces in the image encoding, and the lossless image compression can be accomplished by ruling out the similarity of the pixels.

Method for encoding image using estimation of color space

The present invention relates to a stereoscopic video file format capable of improving bit efficiency and processing efficiency and a computer-readable recording medium in which the corresponding stereoscopic video file are recorded. The present invention includes: a file type box that stores file format information and information indicating whether or not to include monoscopic data; a movie box that stores a plurality of trak boxes configuring stereoscopic video streams; a media data box that stores multimedia resources; a stereoscopic video media information box that stores at least one common stereoscopic video stream arrangement information; a stereoscopic camera and display information reference box that stores camera parameter and recommendation display information referenced by the plurality of trak boxes; a stereoscopic camera and display information box that exists at each stereoscopic image frame of the stereoscopic video stream and stores reference information of the stereoscopic camera and display information reference box; and a meta box that stores metadata, thereby making it possible to minimize overlapping data and optimizing a configuration of a file format in a simple form.

Growing community of inventors

Seongnam-si, South Korea

Je Woo Kim