Patents Assigned to Industry Academy Cooperation Foundation of Sejong University
  • Patent number: 11567491
    Abstract: A device and method for remotely controlling an unmanned aerial vehicle based on reinforcement learning are disclosed. An embodiment provides a device for remotely controlling an unmanned aerial vehicle based on reinforcement learning, where the device includes a processor and a memory connected to the processor, and the memory includes program instructions that can be executed by the processor to determine an inclination direction corresponding to the hand pose of a user, the movement direction of the hand, and the angle in the inclination direction based on sensing data associated with the pose of the hand or the movement of the hand acquired by way of at least one sensor, and determine one of a movement direction, a movement speed, a mode change, a figural trajectory, and a scale of the figural trajectory of the unmanned aerial vehicle according to the determined inclination direction, movement direction, and angle.
    Type: Grant
    Filed: December 2, 2019
    Date of Patent: January 31, 2023
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Yong Guk Kim, Sang Yun Shin, Yong Won Kang
  • Patent number: 11539972
    Abstract: A method and an apparatus for encoding/decoding an image according to the present invention may determine a reference area that is a pre-reconstructed area spatially adjacent to a current block on the basis of reference information for specifying the position of a reference area used for predicting a current block and may predict the current block on the basis of the reference area.
    Type: Grant
    Filed: March 29, 2019
    Date of Patent: December 27, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Hee Moon, Dong Jae Won, Jae Min Ha, Sung Won Lim
  • Publication number: 20220408110
    Abstract: Disclosed herein is a method of decoding an image. The method includes generating an inter prediction block by performing inter prediction with respect to a current block, generating an intra prediction block by performing intra prediction with respect to the current block, determining a first weight and a second weight, and generating a final prediction block by respectively applying the first weight and the second weight to the inter prediction block and the intra prediction block. The generating of the intra prediction block includes generating the intra prediction block using a predefined intra prediction mode.
    Type: Application
    Filed: August 18, 2022
    Publication date: December 22, 2022
    Applicants: Electronics and Telecommunications Research Institute, INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY, CHIPS&MEDIA, INC, INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOREA AEROSPACE UNIVERSITY
    Inventors: Sung Chang LIM, Jung Won KANG, Ha Hyun LEE, Jin Ho LEE, Hui Yong KIM, Yung Lyul LEE, Ji Yeon JUNG, Nam Uk KIM, Myung Jun KIM, Yang Woo KIM, Dae Yeon KIM, Jae Gon KIM
  • Patent number: 11533470
    Abstract: Disclosed are an image encoding/decoding method and apparatus. The image decoding method includes decoding coding mode information of a current coding block, dividing the current coding block into at least one prediction block, and generating prediction samples of the at least one prediction block on the basis of the decoded coding mode, in which the coding mode information is information indicating any one mode among intra mode, inter mode, and hybrid mode.
    Type: Grant
    Filed: January 26, 2021
    Date of Patent: December 20, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Hee Moon, Dong Jae Won, Sung Won Lim
  • Publication number: 20220394251
    Abstract: The present invention discloses a method for constructing a tile structure, wherein a current picture includes at least two or more tiles, the at least two or more tiles are split by a column splitting and a row splitting, at least one or more of the column splitting and the row splitting are performed by using a splitting length which is shorter than a width length or a height length of the current picture.
    Type: Application
    Filed: February 28, 2022
    Publication date: December 8, 2022
    Applicant: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Jong-Ki HAN, Jae-Yung LEE
  • Publication number: 20220385892
    Abstract: A method for decoding an image signal according to the present invention may comprise the steps of: determining whether there is a brightness change between a current image including a current block and a reference image of the current image; if it is determined that there is a brightness change between the current image and the reference image, determining weight prediction parameter candidates for the current block; determining a weight prediction parameter for the current block on the basis of index information which specifies any one of the weight prediction parameter candidates; and performing a prediction on the current block on the basis of the weight prediction parameter.
    Type: Application
    Filed: August 9, 2022
    Publication date: December 1, 2022
    Applicant: Industry Academy Cooperation Foundation of Sejong University
    Inventors: Joo Hee MOON, Sung Won LIM, Dong Jae WON
  • Publication number: 20220385895
    Abstract: The present invention relates to an image encoding/decoding method and apparatus. The image decoding method according to the present invention may comprise acquiring transform coefficients distribution information of a neighboring block from a bitstream; direction-adaptively determining an intra prediction mode of a current block to be decoded, according to the transform coefficients distribution information of the neighboring block; and reconstructing the current block, based on the determined intra prediction mode, wherein the direction-adaptively determining includes determining similarity flag information corresponding to the neighboring block, based on the transform coefficients distribution information of the neighboring block.
    Type: Application
    Filed: August 10, 2022
    Publication date: December 1, 2022
    Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, CHIPS&MEDIA,INC, INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Jin Ho LEE, Jung Won KANG, Ha Hyun LEE, Sung Chang LIM, Hui Yong KIM, Dae Yeon KIM, Yung Lyul LEE
  • Publication number: 20220368901
    Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method, according to the present invention, comprises the steps of: determining a transformation performing region; segmenting the determined transformation performing region into at least one sub-transform block by using at least one of quadtree segmentation and binary tree segmentation; and performing inverse transformation on the at least one sub-transform block.
    Type: Application
    Filed: July 8, 2022
    Publication date: November 17, 2022
    Applicant: Industry Academy Cooperation Foundation of Sejong University
    Inventors: Joo Hee MOON, Dong Jae WON, Sung Won LIM
  • Publication number: 20220345703
    Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method, according to the present invention, comprises the steps of: determining a transformation performing region; segmenting the determined transformation performing region into at least one sub-transform block by using at least one of quadtree segmentation and binary tree segmentation; and performing inverse transformation on the at least one sub-transform block.
    Type: Application
    Filed: July 8, 2022
    Publication date: October 27, 2022
    Applicant: Industry Academy Cooperation Foundation of Sejong University
    Inventors: Joo Hee MOON, Dong Jae WON, Sung Won LIM
  • Publication number: 20220337828
    Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method, according to the present invention, comprises the steps of: decoding information associated with a clipping range of a current block; and performing sample adaptive offset (SAO) filtering on the basis of the information associated with the clipping range, wherein the information associated with the clipping range may include information on the maximum and minimum values of a pixel value included in the current block.
    Type: Application
    Filed: July 4, 2022
    Publication date: October 20, 2022
    Applicant: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Hee MOON, Dong Jae WON, Sung Won LIM
  • Publication number: 20220326373
    Abstract: There is provided a method for aerial analysis of a ground surface. The disclosed method includes: controlling a distance sensor of an unmanned aerial vehicle (UAV) to be successively oriented in a plurality of sensing directions towards the ground surface; and analyzing the ground surface based on distance measurement data indicative of distances measured by the distance sensor in the plurality of sensing directions, the plurality of sensing directions corresponding to respective points defining a planar trajectory, the planar trajectory including a plurality of loops winding an identical inner point.
    Type: Application
    Filed: November 26, 2021
    Publication date: October 13, 2022
    Applicant: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Jin Woo Song, Yeong Seo Kwon, Yong Hun Kim, Do Hoang Viet
  • Patent number: 11466989
    Abstract: A method is described in which a plurality of magnetic field norms is obtained using a plurality of magnetic field sensor units, each of the plurality of magnetic field sensor units being arranged to measure a magnetic field at a different height while being mounted to an object, each of the plurality of magnetic field norms being a norm of the magnetic field measured by a corresponding one of the plurality of magnetic field sensor units; and the plurality of magnetic field norms is matched with a magnetic field map of an indoor area including a plurality of sub-areas to estimate a location of the object as one of the plurality of sub-areas.
    Type: Grant
    Filed: November 2, 2020
    Date of Patent: October 11, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Jin Woo Song, Yong Hun Kim, Eung Ju Kim, Min Jun Choi, Do Hoang Viet
  • Patent number: 11463690
    Abstract: The present invention relates to an image encoding/decoding method and apparatus. The image decoding method according to the present invention may comprise acquiring transform coefficients distribution information of a neighboring block from a bitstream; direction-adaptively determining an intra prediction mode of a current block to be decoded, according to the transform coefficients distribution information of the neighboring block; and reconstructing the current block, based on the determined intra prediction mode, wherein the direction-adaptively determining includes determining similarity flag information corresponding to the neighboring block, based on the transform coefficients distribution information of the neighboring block.
    Type: Grant
    Filed: May 7, 2021
    Date of Patent: October 4, 2022
    Assignees: Electronics and Telecommunications Research Institute, CHIPS & MEDIA, INC, Industry Academy Cooperation Foundation of Sejong University
    Inventors: Jin Ho Lee, Jung Won Kang, Ha Hyun Lee, Sung Chang Lim, Hui Yong Kim, Dae Yeon Kim, Yung Lyul Lee
  • Patent number: 11457238
    Abstract: Disclosed herein is a method of decoding an image. The method includes generating an inter prediction block by performing inter prediction with respect to a current block, generating an intra prediction block by performing intra prediction with respect to the current block, determining a first weight and a second weight, and generating a final prediction block by respectively applying the first weight and the second weight to the inter prediction block and the intra prediction block. The generating of the intra prediction block includes generating the intra prediction block using a predefined intra prediction mode.
    Type: Grant
    Filed: December 27, 2019
    Date of Patent: September 27, 2022
    Assignees: Electronics and Telecommunications Research Institute, INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY, CHIPS & MEDIA, INC, INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOREA AEROSPACE UNIVERSITY
    Inventors: Sung Chang Lim, Jung Won Kang, Ha Hyun Lee, Jin Ho Lee, Hui Yong Kim, Yung Lyul Lee, Ji Yeon Jung, Nam Uk Kim, Myung Jun Kim, Yang Woo Kim, Dae Yeon Kim, Jae Gon Kim
  • Patent number: 11449708
    Abstract: A method of identifying and analyzing materials includes selecting at least two elements, collecting data of a plurality of compounds analyzed to be producible by the at least two elements, preparing image or spectrum-type analysis data for each of the plurality of collected compounds, selecting binary or higher-order compounds from among the plurality of compounds to mix the selected compounds at a predetermined mixing ratio, and generating training data including resultant data obtained by combining and processing the image or spectrum-type analysis data according to the predetermined mixing ratio, performing machine learning using the training data, and identifying and/or analyzing image or spectrum-type analysis data obtained from an actual material, using a model obtained through the machine learning.
    Type: Grant
    Filed: December 6, 2019
    Date of Patent: September 20, 2022
    Assignee: Industry Academy Cooperation Foundation of Sejong University
    Inventors: Kee-sun Sohn, Jin-woong Lee
  • Patent number: 11442180
    Abstract: A method and a system for verifying integrity of GPS position information according to a disclosed embodiment is a method performed in an unmanned moving object including one or more processors and a memory for storing one or more programs executed by the one or more processors. The method includes an operation of performing an authentication process for a connected base station, by the unmanned moving object, an operation of measuring a position of the unmanned moving object by performing wireless communication with a plurality of authenticated base stations, and an operation of verifying the GPS position information by comparing a value of the measured position with a position value of the GPS position information received from a satellite.
    Type: Grant
    Filed: November 29, 2019
    Date of Patent: September 13, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Ji Sun Shin, Byung Woon Park, Shin Cheol Lee, Ye Bin Lee
  • Publication number: 20220272361
    Abstract: A method for decoding an image signal according to the present invention may comprise the steps of: determining whether there is a brightness change between a current image including a current block and a reference image of the current image; if it is determined that there is a brightness change between the current image and the reference image, determining weight prediction parameter candidates for the current block; determining a weight prediction parameter for the current block on the basis of index information which specifies any one of the weight prediction parameter candidates; and performing a prediction on the current block on the basis of the weight prediction parameter.
    Type: Application
    Filed: May 13, 2022
    Publication date: August 25, 2022
    Applicant: Industry Academy Cooperation Foundation of Sejong University
    Inventors: Joo Hee MOON, Sung Won LIM, Dong Jae WON
  • Publication number: 20220272390
    Abstract: There is provided a video signal decoding method. The method comprises decoding block division information of a current block, dividing the current block into a plurality of sub blocks based on the block division information, and decoding the sub blocks.
    Type: Application
    Filed: April 8, 2022
    Publication date: August 25, 2022
    Applicant: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Yung Lyul LEE, Nam Uk KIM, Kyung Hwan KO, Young Hwan YOO
  • Patent number: 11425426
    Abstract: The present invention relates to an image encoding/decoding method and device, and the image encoding method or device according to an embodiment of the present invention may encode a position of a reference coefficient within a current transform block to be encoded, and encoding skip region information of a skip region selected on the basis of the position of the reference coefficient. The skip region information may represent whether or not coefficients within the skip region have an identical coefficient value.
    Type: Grant
    Filed: January 31, 2018
    Date of Patent: August 23, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Hee Moon, Jae Min Ha, Dong Jae Won, Sung Won Lim
  • Patent number: 11412218
    Abstract: The present invention provides an image encoding method and an image decoding method. The image decoding method, according to the present invention, comprises the steps of: decoding information associated with a clipping range of a current block; and performing sample adaptive offset (SAO) filtering on the basis of the information associated with the clipping range, wherein the information associated with the clipping range may include information on the maximum and minimum values of a pixel value included in the current block.
    Type: Grant
    Filed: January 16, 2018
    Date of Patent: August 9, 2022
    Assignee: INDUSTRY ACADEMY COOPERATION FOUNDATION OF SEJONG UNIVERSITY
    Inventors: Joo Hee Moon, Dong Jae Won, Sung Won Lim