Patents Assigned to Kwangwoon University Industry-Academic Collaboration Foundation
  • APPARATUS AND METHOD OF DATA GENERATION FOR OBJECT DETECTION BASED ON GENERATIVE ADVERSARIAL NETWORKS
    Publication number: 20200012896
    Abstract: Provided is an apparatus for generating data based on generative adversarial networks (GANs), the apparatus including a first generator configured to receive input data and generate a first fake image and a first discriminator configured to receive the first fake image generated by the first generator and a first real image and verify whether an image is fake or real.
    Type: Application
    Filed: December 4, 2018
    Publication date: January 9, 2020
    Applicant: Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Ji Sang YOO, Ju Won KWON
  • APPARATUS FOR ENCODING AND DECODING OF INTEGRATED SPEECH AND AUDIO
    Publication number: 20190385621
    Abstract: Provided is an encoding apparatus for integrally encoding and decoding a speech signal and a audio signal, and may include: an input signal analyzer to analyze a characteristic of an input signal; a stereo encoder to down mix the input signal to a mono signal when the input signal is a stereo signal, and to extract stereo sound image information; a frequency band expander to expand a frequency band of the input signal; a sampling rate converter to convert a sampling rate; a speech signal encoder to encode the input signal using a speech encoding module when the input signal is a speech characteristics signal; a audio signal encoder to encode the input signal using a audio encoding module when the input signal is a audio characteristic signal; and a bitstream generator to generate a bitstream.
    Type: Application
    Filed: August 30, 2019
    Publication date: December 19, 2019
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Tae Jin LEE, Seung-Kwon BAEK, Min Je KIM, Dae Young JANG, Jeongil SEO, Kyeongok KANG, Jin-Woo HONG, Hochong PARK, Young-Cheol PARK
  • Method and apparatus for employing dynamic range mapping information for HDR image decoder considering backward compatibility
    Patent number: 10477252
    Abstract: The present invention enables efficient decoding by using DR mapping information between a base layer and an enhancement layer in various manners in an HDR decoder considering backward compatibility.
    Type: Grant
    Filed: June 15, 2016
    Date of Patent: November 12, 2019
    Assignee: Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Donggyu Sim, Seanae Park, Yongjo Ahn, Jonghyun Ma, Jeongyun Lim
  • Method for decoding video using in-loop filter, and device therefor
    Patent number: 10477247
    Abstract: The present invention provides a method and apparatus for encoding/decoding an image and for adjusting a reconstructed pixel by scaling an offset of an in-loop filter having a scaled offset value. The method includes: obtaining information of a scale default value of a current block from a bitstream; obtaining offset parameter merge information of the current block from the bitstream; obtaining the offset parameter of the current block on the basis of the offset parameter merge information; determining whether a scale residual value of the current block is obtained from the bitstream on the basis of the offset parameter merge information; obtaining a scale value on the basis of the scale default value and the scale residual value; scaling an offset on the basis of the offset parameter and the scale value; and adjusting a pixel value of the current block on the basis of the scaled offset.
    Type: Grant
    Filed: November 18, 2016
    Date of Patent: November 12, 2019
    Assignees: Electronics and Telecommunications Research Institute, Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Jung Won Kang, Hyun Suk Ko, Sung Chang Lim, Jin Ho Lee, Dong San Jun, Hui Yong Kim, Dong Gyu Sim, Seoung Jun Oh, Jin Soo Choi, Seoung Hwi Kim, Sea Nae Park, Yong Jo Ahn, Dong Kyu Lee
  • Motion picture encoding apparatus and method thereof
    Patent number: 10469840
    Abstract: Provided is a video encoding apparatus, including a signal separator to separate a differential image block into a first domain and a second domain, based on a boundary line included in the differential image block, the differential image block indicating a difference between an original image and a prediction image with respect to the original image, a transform encoder to perform a transform encoding with respect to the first domain using a discrete cosine transform (DCT), a quantization unit to quantize an output of the transform encoding unit in a frequency domain, a space domain quantization unit to quantize the second domain in a space domain, and an entropy encoder to perform an entropy encoding using outputs of the quantization unit and the space domain quantization unit.
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: November 5, 2019
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION, KOREA-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY, KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
    Inventors: Sung-Chang Lim, Ha Hyun Lee, Hui Yong Kim, Se Yoon Jeong, Suk Hee Cho, Hae Chul Choi, Jong Ho Kim, Jin Ho Lee, Jin Soo Choi, Jin Woo Hong, Dong Gyu Sim, Seoung Jun Oh, Gwang Hoon Park, Mun Churl Kim, Neung Joo Hwang, Sea Nae Park
  • Method and apparatus for encoding/decoding video by using padding in video codec
    Patent number: 10469843
    Abstract: The present invention relates to a method and apparatus for encoding/decoding a video, the method being applied with a method of using video padding and removing the padded area after decoding in order to effectively encode the video in a video compression technology for a high-definition security camera.
    Type: Grant
    Filed: February 13, 2018
    Date of Patent: November 5, 2019
    Assignee: Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Donggyu Sim, Seanae Park
  • VIDEO DECODER AND CONTROLLING METHOD THEREOF
    Publication number: 20190238873
    Abstract: The present invention relates to a video decoder and controlling method thereof. Particularly, the present invention is characterized in dividing a block into subblocks of a prescribed unit, selecting prescribed subblocks according to a priority, and decoding the selected prescribed subblocks.
    Type: Application
    Filed: January 30, 2018
    Publication date: August 1, 2019
    Applicants: LG ELECTRONICS INC., KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Kyungyong KIM, Donggyu SIM, Hongsuk JEONG, Seungchul JANG, Seanae PARK, Juntaek PARK
  • Method and an apparatus for encoding/decoding residual coefficient
    Patent number: 10356413
    Abstract: The encoding/decoding method and apparatus according to the present invention derives a residual coefficient of a residual block, calculates a quantization parameter for a residual block, performs dequantization on a residual coefficient using a quantization parameter, and performs inverse transform on a dequantized residual coefficient to reconstruct a residual sample of a residual block.
    Type: Grant
    Filed: November 8, 2018
    Date of Patent: July 16, 2019
    Assignee: KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Dong Gyu Sim, Sea Nae Park
  • Image encoder and decoder using unidirectional prediction
    Patent number: 10321137
    Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.
    Type: Grant
    Filed: October 7, 2016
    Date of Patent: June 11, 2019
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Hae Chul Choi, Se Yoon Jeong, Sung-Chang Lim, Jin Soo Choi, Jin Woo Hong, Dong Gyu Sim, Seoung-Jun Oh, Chang-Beom Ahn, Gwang Hoon Park, Seung Ryong Kook, Sea-Nae Park, Kwang-Su Jeong
  • Intra scene prediction method of depth image for interlayer video decoding and encoding apparatus and method
    Patent number: 10284876
    Abstract: An inter-layer video decoding method according to an embodiment of the present invention may comprise the steps of: obtaining prediction mode information for a current block of a depth image from a bitstream; creating a prediction block of the current block on the basis of the obtained prediction mode information; predicting an average value for the prediction block by using the pixel values of a designated location of the prediction block; and decoding the depth image by using the average value for the prediction block.
    Type: Grant
    Filed: July 18, 2014
    Date of Patent: May 7, 2019
    Assignees: SAMSUNG ELECTRONICS CO., LTD, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Jin-young Lee, Dong-gyu Sim, Woong Lim, Hyun-ho Jo, Byeong-doo Choi, Min-woo Park, Yong-jin Cho
  • APPARATUS AND METHOD FOR ENCODING AND DECODING OF INTEGRATED SPEECH AND AUDIO
    Publication number: 20190074022
    Abstract: Provided are an apparatus and a method for integrally encoding and decoding a speech signal and a audio signal.
    Type: Application
    Filed: November 2, 2018
    Publication date: March 7, 2019
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Tae Jin LEE, Seung-Kwon BAEK, Min Je KIM, Dae Young JANG, Jeongil SEO, Kyeongok KANG, Jin-Woo HONG, Hochong PARK, Young-cheol PARK
  • METHOD FOR CODING AND DECODING SCALABLE VIDEO AND APPARATUS USING SAME
    Publication number: 20190058891
    Abstract: The present invention relates to a method and an apparatus for interlayer prediction, and the method for interlayer prediction, according to the present invention, comprises the steps of: deciding whether to apply an interlayer prediction to an enhancement layer; and performing a prediction on a current block of the enhancement layer based on reference information that is generalized and generated from a reference picture, which is decoded, of a reference layer, when the interlayer prediction is applied, wherein the reference layer information can be encoding information of a reference block, which corresponds to a current block of the enhancement layer, from the reference layer, and residual information.
    Type: Application
    Filed: October 22, 2018
    Publication date: February 21, 2019
    Applicants: Electronics and Telecommunications Research Institute, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Ha Hyun LEE, Jung Won KANG, Jin Soo CHOI, Jin Woong KIM, Dong Gyu SIM, Hyo Min CHOI, Jung Hak NAM
  • Egomotion estimation system and method
    Patent number: 10187630
    Abstract: An egomotion estimation system may include: a stereo camera suitable for acquiring a stereo image; a map generation unit suitable for generating a depth map and a disparity map using the stereo image; a feature point extraction unit suitable for extracting a feature point from a moving object in the stereo image using the disparity map; a motion vector detection unit suitable for detecting a motion vector of the extracted feature vector point; an error removing unit suitable for removing an error of the detected motion vector; and an egomotion determination unit suitable for calculating and determine an egomotion using the error-removed motion vector.
    Type: Grant
    Filed: April 27, 2016
    Date of Patent: January 22, 2019
    Assignees: SK Hynix Inc., KWANGWOON UNIVERSITY INDUSTRY ACADEMIC COLLABORATION FOUNDATION
    Inventors: Ji Sang Yoo, Seung Woo Seo
  • Image encoder and decoder using unidirectional prediction
    Patent number: 10178393
    Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.
    Type: Grant
    Filed: October 7, 2016
    Date of Patent: January 8, 2019
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Hae Chul Choi, Se Yoon Jeong, Sung-Chang Lim, Jin Soo Choi, Jin Woo Hong, Dong Gyu Sim, Seoung-Jun Oh, Chang-Beom Ahn, Gwang Hoon Park, Seung Ryong Kook, Sea-Nae Park, Kwang-Su Jeong
  • METHOD FOR DECODING VIDEO USING IN-LOOP FILTER, AND DEVICE THEREFOR
    Publication number: 20180359491
    Abstract: The present invention provides a method and apparatus for encoding/decoding an image and for adjusting a reconstructed pixel by scaling an offset of an in-loop filter having a scaled offset value. The method includes: obtaining information of a scale default value of a current block from a bitstream; obtaining offset parameter merge information of the current block from the bitstream; obtaining the offset parameter of the current block on the basis of the offset parameter merge information; determining whether a scale residual value of the current block is obtained from the bitstream on the basis of the offset parameter merge information; obtaining a scale value on the basis of the scale default value and the scale residual value; scaling an offset on the basis of the offset parameter and the scale value; and adjusting a pixel value of the current block on the basis of the scaled offset.
    Type: Application
    Filed: November 18, 2016
    Publication date: December 13, 2018
    Applicants: Electronics and Telecommunications Research Institute, Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Jung Won KANG, Hyun Suk KO, Sung Chang LIM, Jin Ho LEE, Dong San JUN, Hui Yong KIM, Dong Gyu SIM, Seoung Jun OH, Jin Soo CHOI, Seoung Hwi KIM, Sea Nae PARK, Yong Jo AHN, Dong Kyu LEE
  • Method for coding and decoding scalable video and apparatus using same
    Patent number: 10142648
    Abstract: The present invention relates to a method and an apparatus for interlayer prediction, and the method for interlayer prediction, according to the present invention, comprises the steps of: deciding whether to apply an interlayer prediction to an enhancement layer; and performing a prediction on a current block of the enhancement layer based on reference information that is generalized and generated from a reference picture, which is decoded, of a reference layer, when the interlayer prediction is applied, wherein the reference layer information can be encoding information of a reference block, which corresponds to a current block of the enhancement layer, from the reference layer, and residual information.
    Type: Grant
    Filed: May 3, 2017
    Date of Patent: November 27, 2018
    Assignees: Electronics and Telecommunications Research Institute, Kwangwoon University Industry-Academic Collaboration Foundation
    Inventors: Ha Hyun Lee, Jung Won Kang, Jin Soo Choi, Jin Woong Kim, Dong Gyu Sim, Hyo Min Choi, Jung Hak Nam
  • Apparatus and method for encoding and decoding of integrated speech and audio utilizing a band expander with a spectral band replication (SBR) to output the SBR to either time or transform domain encoding according to the input signal characteristic
    Patent number: 10121482
    Abstract: Provided are an apparatus and a method for integrally encoding and decoding a speech signal and an audio signal. The encoding apparatus may include: an input signal analyzer to analyze a characteristic of an input signal; a first conversion encoder to convert the input signal to a frequency domain signal, and to encode the input signal when the input signal is an audio characteristic signal; a Linear Predictive Coding (LPC) encoder to perform LPC encoding of the input signal when the input signal is a speech characteristic signal; a frequency band expander for expanding a frequency band of the input signal whose output is transmitted to either the time-domain encoding module or the transform encoding module based on the input characteristic; and a bitstream generator to generate a bitstream using an output signal of the first conversion encoder and an output signal of the LPC encoder.
    Type: Grant
    Filed: June 9, 2017
    Date of Patent: November 6, 2018
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Tae Jin Lee, Seung-Kwon Baek, Min Je Kim, Dae Young Jang, Jeongil Seo, Kyeongok Kang, Jin-Woo Hong, Hochong Park, Young-cheol Park
  • UNIFIED SPEECH/AUDIO CODEC (USAC) PROCESSING WINDOWS SEQUENCE BASED MODE SWITCHING
    Publication number: 20180261235
    Abstract: A Unified Speech and Audio Codec (USAC) that may process a window sequence based on mode switching is provided. The USAC may perform encoding or decoding by overlapping between frames based on a folding point when mode switching occurs. The USAC may process different window sequences for each situation to perform encoding or decoding, and thereby may improve a coding efficiency.
    Type: Application
    Filed: May 15, 2018
    Publication date: September 13, 2018
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Seungkwon BEACK, Tae Jin LEE, Min Je KIM, Kyeongok KANG, Dae Young JANG, Jeongil SEO, Jin Woo HONG, Chieteuk AHN, Ho Chong PARK, Young-cheol PARK
  • MOTION PICTURE ENCODING APPARATUS AND METHOD THEREOF
    Publication number: 20180213227
    Abstract: Provided is a video encoding apparatus, including a signal separator to separate a differential image block into a first domain and a second domain, based on a boundary line included in the differential image block, the differential image block indicating a difference between an original image and a prediction image with respect to the original image, a transform encoder to perform a transform encoding with respect to the first domain using a discrete cosine transform (DCT), a quantization unit to quantize an output of the transform encoding unit in a frequency domain, a space domain quantization unit to quantize the second domain in a space domain, and an entropy encoder to perform an entropy encoding using outputs of the quantization unit and the space domain quantization unit.
    Type: Application
    Filed: March 22, 2018
    Publication date: July 26, 2018
    Applicants: Electronics and Telecommunications Research Institute, Kwangwoon University Industry-Academic Collaboration Foundation, University-Industry Cooperation Group of Kyung Hee University, Korea Advanced Institute of Science and Technology
    Inventors: Sung-Chang LIM, Ha Hyun LEE, Hui Yong KIM, Se Yoon JEONG, Suk Hee CHO, Hae Chul CHOI, Jong Ho KIM, Jin Ho LEE, Jin Soo CHOI, Jin Woo HONG, Dong Gyu SIM, Seoung Jun OH, Gwang Hoon PARK, Mun Churl KIM, Neung Joo HWANG, Sea Nae PARK
  • INTER-LAYER PREDICTION METHOD FOR MULTI-LAYER VIDEO AND DEVICE THEREFOR
    Publication number: 20180213252
    Abstract: An inter-layer prediction method and device for a multi-layer video. The inter-layer prediction method includes the steps of: generating a restored picture in a reference layer through the predictive coding of the reference layer, determining when there is a restored picture in the reference layer for the time corresponding to a current picture in an enhancement layer for coding or decoding of the current picture in the enhancement layer, and performing inter-layer prediction by referencing a picture in the enhancement layer or a restored picture in the reference layer, depending on whether there is restored picture from the same view in the reference layer.
    Type: Application
    Filed: March 23, 2018
    Publication date: July 26, 2018
    Applicant: KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION
    Inventors: Kyeong Hye KIM, Hyun Ho JO, Jung Hak NAM, Dong Gyu SIM