Patents by Inventor Duck-hoon Kim

Duck-hoon Kim 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).

  • Publication number: 20250078690
    Abstract: A display substrate according to the embodiment includes a base material containing chromium and iron, wherein the base material includes a surface portion and a central portion, the surface portion is defined as a depth region from a surface of the base material to a depth of 5 nm in a thickness direction of the base material, and a ratio of chromium atoms to iron atoms (Cr/Fe) of the surface portion is greater than that of the central portion.
    Type: Application
    Filed: November 18, 2024
    Publication date: March 6, 2025
    Inventors: Hae Sik KIM, Duck Hoon Park, Hyun Joon Jung
  • Patent number: 12232408
    Abstract: A substrate for display comprises one surface, the other surface, a first area (folding area) and a second area (non-folding area). A first hole passing through the one surface and the other surface is formed on the first area. A 1-1 groove is formed on one surface of the first area in the direction from the one surface to the other surface. A 1-2 groove is formed on the other surface of the first area in the direction from the other surface to the one surface. A 2-1 groove is formed on one surface of the second area in the direction from the one surface to the other surface. A 2-2 groove is formed on the other surface of the second area in the direction from the other surface to the one surface. The 1-1 groove and 1-2 groove and the 2-1 groove and 2-2 groove do not overlap each other in the thickness direction of the substrate for display.
    Type: Grant
    Filed: July 27, 2020
    Date of Patent: February 18, 2025
    Assignee: LG INNOTEK CO., LTD.
    Inventors: Duck Hoon Park, Hae Sik Kim, Woo Young Chang, Jee Heum Paik
  • Publication number: 20250054418
    Abstract: A display substrate according to an embodiment relates to a display substrate comprising a display panel installation area and a bezel area. The display substrate comprises one surface and the other surface opposite to the one surface, and the display substrate comprises: a first area which is defined as a folding area; and a second area which is defined as an unfolding area, wherein a groove is formed on the one surface or the other surface of the display substrate and formed in the display panel installation area of the first area, and a hole is formed through the one surface and the other surface of the display substrate and formed in the bezel area of the first area.
    Type: Application
    Filed: October 28, 2024
    Publication date: February 13, 2025
    Inventors: Duck Hoon PARK, Hae Sik Kim, Jee Heum Paik, Sung Won Kang
  • Publication number: 20240394914
    Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, a method includes receiving images of a vehicle and determining locations of key points of the vehicle within the keyframes. Pose estimations may then be determined based on the key point locations, and a three-dimensional contour of the vehicle may be determined based on the pose estimations. A model may then be trained based on the three-dimensional contour of the vehicle. Other aspects and features are also claimed and described.
    Type: Application
    Filed: May 22, 2023
    Publication date: November 28, 2024
    Inventors: Jeong-Kyun Lee, Young-Ki Baik, Yongho Shin, Sueyeon Kim, Duck Hoon Kim
  • Patent number: 11948249
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Grant
    Filed: October 7, 2022
    Date of Patent: April 2, 2024
    Assignee: QUALCOMM Incorporated
    Inventors: Young-Ki Baik, ChaeSeong Lim, Duck Hoon Kim
  • Publication number: 20230135153
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Application
    Filed: October 7, 2022
    Publication date: May 4, 2023
    Inventors: Young-Ki BAIK, ChaeSeong LIM, Duck Hoon KIM
  • Patent number: 11630197
    Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: April 18, 2023
    Assignee: QUALCOMM Incorporated
    Inventors: Jayakrishnan Unnikrishnan, Avdhut Joshi, Shivam Agarwal, Amir Salimi, Sree Sesha Aravind Vadrevu, Gautam Sachdeva, Yoga Y Nadaraajan, Ravi Teja Sukhavasi, Xinzhou Wu, Young-Ki Baik, Duck Hoon Kim, Hyun-Mook Cho
  • Publication number: 20230112799
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Application
    Filed: October 18, 2022
    Publication date: April 13, 2023
    Inventors: Young-Ki BAIK, Hyun-Mook CHO, Duck Hoon KIM, Jeong-Kyun LEE, Chaeseong LIM, Hee-Seok LEE
  • Patent number: 11544940
    Abstract: Disclosed are techniques for lane estimation. In aspects, a method includes receiving a plurality of camera frames captured by a camera sensor of a vehicle, assigning a first subset of the plurality of camera frames to a deep learning (DL) detector and a second subset of the plurality of camera frames to a computer vision (CV) detector based on availability of the DL and CV detectors, identifying a first set of lane boundary lines in a first camera frame processed by the DL detector, identifying a second set of lane boundary lines in a second camera frame processed by the CV detector, generating first and second sets of lane models based on the first and second sets of lane boundary lines, and updating a set of previously identified lane models based on the first set of lane models and/or the second set of lane models.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: January 3, 2023
    Assignee: QUALCOMM Incorporated
    Inventors: Young-Ki Baik, Jeong-Kyun Lee, Seok-Soo Hong, Duck Hoon Kim
  • Patent number: 11508122
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: November 22, 2022
    Assignee: QUALCOMM Incorporated
    Inventors: Young-Ki Baik, Hyun-Mook Cho, Duck Hoon Kim, Jeong-Kyun Lee, ChaeSeong Lim, Hee-Seok Lee
  • Patent number: 11494979
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: November 8, 2022
    Assignee: QUALCOMM Incorporated
    Inventors: Young-Ki Baik, ChaeSeong Lim, Duck Hoon Kim
  • Patent number: 11475678
    Abstract: Disclosed are techniques for performing lane instance recognition. Lane instances are difficult to recognize since they are long and elongated, and they also look different from view to view. An approach is proposed in which local mask segmentation lane estimation and global control points lane estimation are combined.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: October 18, 2022
    Assignee: QUALCOMM Incorporated
    Inventors: Heesoo Myeong, Hee-Seok Lee, Duck Hoon Kim, Seungwoo Yoo, Kang Kim
  • Patent number: 11195028
    Abstract: Disclosed are techniques for estimating multiple lane boundaries through simultaneous detection of lane markers (LM) and raised pavement markers (RPM). Conventional techniques for lane marker detection (LMD) comprises extracting and clustering line segments from a camera image, fitting the clustered lines to a geometric model, and selecting the multiple lanes using heuristic approaches. Unfortunately, in the conventional technique, an error from each step is sequentially propagated to the next step. Also there are no techniques to estimate both LMs and RPMs. A technique to simultaneously detect in real time both LM and RPMs is proposed. This enables optimal estimation of multiple lane boundaries.
    Type: Grant
    Filed: January 2, 2020
    Date of Patent: December 7, 2021
    Assignee: QUALCOMM Incorporated
    Inventors: Jeong-Kyun Lee, Young-Ki Baik, Seungwoo Yoo, Duck Hoon Kim
  • Patent number: 10867189
    Abstract: An electronic device is described. The electronic device includes a memory and a processor in communication with the memory. The processor is configured to receive an image. The processor is also configured to extract a lane response map from the image. The processor is further configured to estimate one or more lane markers based on the lane response map.
    Type: Grant
    Filed: July 25, 2017
    Date of Patent: December 15, 2020
    Assignee: QUALCOMM Incorporated
    Inventors: Seungwoo Yoo, Duck Hoon Kim
  • Publication number: 20200218908
    Abstract: Disclosed are techniques for estimating multiple lane boundaries through simultaneous detection of lane markers (LM) and raised pavement markers (RPM). Conventional techniques for lane marker detection (LMD) comprises extracting and clustering line segments from a camera image, fitting the clustered lines to a geometric model, and selecting the multiple lanes using heuristic approaches. Unfortunately, in the conventional technique, an error from each step is sequentially propagated to the next step. Also there are no techniques to estimate both LMs and RPMs. A technique to simultaneously detect in real time both LM and RPMs is proposed. This enables optimal estimation of multiple lane boundaries.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Jeong-Kyun LEE, Young-Ki BAIK, Seungwoo YOO, Duck Hoon KIM
  • Publication number: 20200219316
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Young-Ki BAIK, Hyun-Mook CHO, Duck Hoon KIM, Jeong-Kyun LEE, ChaeSeong LIM, Hee-Seok LEE
  • Publication number: 20200218907
    Abstract: Disclosed are techniques for lane estimation. In aspects, a method includes receiving a plurality of camera frames captured by a camera sensor of a vehicle, assigning a first subset of the plurality of camera frames to a deep learning (DL) detector and a second subset of the plurality of camera frames to a computer vision (CV) detector based on availability of the DL and CV detectors, identifying a first set of lane boundary lines in a first camera frame processed by the DL detector, identifying a second set of lane boundary lines in a second camera frame processed by the CV detector, generating first and second sets of lane models based on the first and second sets of lane boundary lines, and updating a set of previously identified lane models based on the first set of lane models and/or the second set of lane models.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Young-Ki BAIK, Jeong-Kyun LEE, Seok-Soo HONG, Duck Hoon Kim
  • Publication number: 20200219315
    Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Young-Ki BAIK, ChaeSeong LIM, Duck Hoon KIM
  • Publication number: 20200218909
    Abstract: Disclosed are techniques for performing lane instance recognition. Lane instances are difficult to recognize since they are long and elongated, and they also look different from view to view. An approach is proposed in which local mask segmentation lane estimation and global control points lane estimation are combined.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Heesoo MYEONG, Hee-Seok LEE, Duck Hoon KIM, Seungwoo YOO, Kang KIM
  • Publication number: 20200218913
    Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.
    Type: Application
    Filed: January 2, 2020
    Publication date: July 9, 2020
    Inventors: Jayakrishnan UNNIKRISHNAN, Avdhut JOSHI, Shivam AGARWAL, Amir SALIMI, Sree Sesha Aravind VADREVU, Gautam SACHDEVA, Yoga Y NADARAAJAN, Ravi Teja SUKHAVASI, Aolin XU, Xinzhou WU, Young-Ki BAIK, Duck Hoon KIM, Hyun-Mook CHO