Patents by Inventor Gi-Mun Um

Gi-Mun Um has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11910013
    Abstract: 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.
    Type: Grant
    Filed: December 30, 2022
    Date of Patent: February 20, 2024
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
  • Patent number: 11910014
    Abstract: 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.
    Type: Grant
    Filed: December 30, 2022
    Date of Patent: February 20, 2024
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
  • Patent number: 11902575
    Abstract: 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.
    Type: Grant
    Filed: August 24, 2022
    Date of Patent: February 13, 2024
    Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
  • Patent number: 11900561
    Abstract: 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.
    Type: Grant
    Filed: November 22, 2021
    Date of Patent: February 13, 2024
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY
    Inventors: Gi Mun Um, Hee Kyung Lee, Dae-Young Song, Donghyeon Cho
  • Patent number: 11694303
    Abstract: 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.
    Type: Grant
    Filed: March 18, 2020
    Date of Patent: July 4, 2023
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Hee Kyung Lee, Gi Mun Um, Jeong Il Seo, Seong Yong Lim, Joung Il Yun, Won Sik Cheong
  • Publication number: 20230156220
    Abstract: 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.
    Type: Application
    Filed: December 30, 2022
    Publication date: May 18, 2023
    Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
  • Publication number: 20230133166
    Abstract: 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.
    Type: Application
    Filed: December 30, 2022
    Publication date: May 4, 2023
    Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
  • Publication number: 20230098276
    Abstract: 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.
    Type: Application
    Filed: September 23, 2022
    Publication date: March 30, 2023
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)
    Inventors: Hee-Kyung LEE, Gi-Mun UM, Dae-Young SONG, Dong-Hyeon CHO
  • Publication number: 20220408111
    Abstract: 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.
    Type: Application
    Filed: August 24, 2022
    Publication date: December 22, 2022
    Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
  • Patent number: 11523133
    Abstract: 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.
    Type: Grant
    Filed: March 30, 2021
    Date of Patent: December 6, 2022
    Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
  • Publication number: 20220222774
    Abstract: 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.
    Type: Application
    Filed: January 11, 2022
    Publication date: July 14, 2022
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Gi-Mun UM, Seong-Yong LIM, Hee-Kyung LEE
  • Publication number: 20220164922
    Abstract: 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.
    Type: Application
    Filed: November 22, 2021
    Publication date: May 26, 2022
    Inventors: Gi Mun UM, Hee Kyung LEE, Dae-Young SONG, Donghyeon CHO
  • Patent number: 11276142
    Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.
    Type: Grant
    Filed: May 13, 2020
    Date of Patent: March 15, 2022
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Joung-Il Yun, Sang-Woon Kwak, Won-Sik Cheong, Gi-Mun Um
  • Publication number: 20210218993
    Abstract: 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.
    Type: Application
    Filed: March 30, 2021
    Publication date: July 15, 2021
    Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY
    Inventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
  • Patent number: 10992956
    Abstract: 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.
    Type: Grant
    Filed: January 15, 2020
    Date of Patent: April 27, 2021
    Assignees: Electronics and Telecommunications Research Institute, University-Industry Cooperation Group of Kyung Hee University
    Inventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
  • Publication number: 20200410638
    Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.
    Type: Application
    Filed: May 13, 2020
    Publication date: December 31, 2020
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: JOUNG-IL YUN, Sang-Woon KWAK, Won-Sik CHEONG, Gi-Mun UM
  • Patent number: 10825185
    Abstract: 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.
    Type: Grant
    Filed: November 28, 2018
    Date of Patent: November 3, 2020
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Kwang Yong Kim, Sang Joon Park, Gi Mun Um, Chang Eun Lee
  • Publication number: 20200302575
    Abstract: 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.
    Type: Application
    Filed: March 18, 2020
    Publication date: September 24, 2020
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Hee Kyung LEE, Gi Mun UM, Jeong Il SEO, Seong Yong LIM, Joung Il YUN, Won Sik CHEONG
  • Publication number: 20200288102
    Abstract: Provided are an image processing method and apparatus for generating a three-dimensional (3D) virtual viewpoint image by combining multi-view depth map on a 3D space through depth clustering. In the image processing method and apparatus, pieces of color and depth information are stored in units of depth clusters to minimize influences of occlusion regions and holes during generating of the virtual viewpoint image.
    Type: Application
    Filed: February 24, 2020
    Publication date: September 10, 2020
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Gi Mun UM, Joung Il YUN
  • Publication number: 20200226716
    Abstract: There is provided an image processing apparatus and method. The image processing apparatus comprises: receiving a first source image and a second source image from multiple image sources, receiving geometric information required for stitching the first source image and the second source image and synthesizing an image from the first source image and the second source image on the basis of the geometric information, wherein the geometric information includes seam information used to specify a overlapping region between the first source image and the second source image.
    Type: Application
    Filed: December 30, 2019
    Publication date: July 16, 2020
    Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Gi Mun UM, Hee Kyung LEE, Jeong Il SEO, Joung Il YUN, Seong Yong LIM, Won Sik CHEONG