公开(公告)号：US20200169691A1

公开(公告)日：2020-05-28

申请号：US16695886

申请日：2019-11-26

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Se-Yoon JEONG ,  Min Hyuk KIM ,  Shinyoung YI ,  Jung-Won KANG ,  Hui-Yong KIM ,  Hakyeong KIM

IPC: H04N7/00 ,  H04N5/58

Abstract: Disclosed herein are a method and apparatus for luminance-adaptive opto-electrical transfer and luminance-adaptive electro-optical transfer. For video transmission and compression, opto-electrical transfer and electro-optical transfer are required. The surround luminance and luminance range of an image are taken into consideration when performing opto-electrical transfer and electro-optical transfer. An opto-electrical transfer function may be derived based on a contrast sensitivity function that takes into consideration the surround luminance of an image. Also, parameters relevant to surround luminance may be signaled from an encoding apparatus to a decoding apparatus, and an electro-optical transfer function may be derived based on the parameters.

公开(公告)号：US20230206551A1

公开(公告)日：2023-06-29

申请号：US18172716

申请日：2023-02-22

Applicant: Samsung Electronics Co., Ltd. ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Min Hyuk KIM ,  Joo Ho LEE ,  Hyun Jin KU ,  Dahyun KANG ,  Hyunho HA

IPC: G06T17/00 ,  G06T3/40 ,  G06V10/141 ,  G06V10/60 ,  G06V10/74 ,  G06V10/762 ,  H04N23/56

CPC classification number: G06T17/00 ,  G06T3/40 ,  G06V10/141 ,  G06V10/60 ,  G06V10/761 ,  G06V10/762 ,  H04N23/56 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20016

Abstract: An electronic device and a control method thereof are provided. The electronic device includes a camera, a camera flash, and at least one processor configured to control the camera to capture a natural light image and a depth image of an object, control the camera and the camera flash to capture an artificial light image of the object, obtain distance information from the depth image to generate a depth mask image, create a cluster mask image from the natural light image, obtain a flash image in which the illuminance of the natural light image has been removed from the illuminance of the artificial light image, obtain an optimization parameter based on the distance information, the depth mask image, the cluster mask image, and the flash image, and obtain three-dimensional topographic information and surface reflection information about the object based on the obtained optimization parameter.

公开(公告)号：US20190096044A1

公开(公告)日：2019-03-28

申请号：US16140347

申请日：2018-09-24

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Seung-Hwan BAEK ,  Incheol KIM

IPC: G06T5/00 ,  G01J3/28 ,  G02B27/10

Abstract: A method for reconstructing a hyperspectral image and a system therefor are provided. The method includes obtaining a dispersion model for dispersion created by a prism included in a camera, the prism including no coded aperture, and reconstructing a hyperspectral image corresponding to a captured image based on the dispersion model.

公开(公告)号：US20220321859A1

公开(公告)日：2022-10-06

申请号：US17656049

申请日：2022-03-23

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Meuleman ANDREAS ,  Hyeonjoong JANG

IPC: H04N13/128 ,  H04N13/243 ,  H04N13/293 ,  H04N13/15 ,  H04N13/111

Abstract: Provided is a real-time omnidirectional stereo matching method in a camera system including a first pair of fisheye cameras including first and second fisheye cameras provided to perform shooting in opposite directions and a second pair of fisheye cameras including third and fourth fisheye cameras provided to perform shooting in opposite directions and in which the first pair of fisheye cameras and the second pair of fisheye cameras are vertically provided, including receiving fisheye images of a subject captured through the first to the fourth fisheye cameras; selecting one fisheye camera from among fisheye cameras for each pixel of a preset reference fisheye image among the fisheye images using a sweep volume for preset distance candidates; generating a distance map for all pixels using the reference fisheye image and a fisheye image of the one fisheye camera; and performing real-time stereo matching on the fisheye images using the distance map.

公开(公告)号：US20210358211A1

公开(公告)日：2021-11-18

申请号：US16622234

申请日：2019-10-07

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Min Hyuk KIM ,  Giljoo NAM

IPC: G06T17/20 ,  G06T7/586

Abstract: Disclosed are herein a three-dimensional (3D) object acquisition method and an object acquisition apparatus using artificial light photographs. A 3D object acquisition method according to an embodiment of the present invention includes receiving a plurality of images of a 3D object photographed by a camera, reconstructing spatially-varying bidirectional reflectance distribution functions for the 3D object based on the plurality of images received, estimating shading normals for the 3D object based on the reconstructed spatially-varying bidirectional reflectance distribution functions, and acquiring 3D geometry for the 3D object based on the estimated shading normals.

公开(公告)号：US20190199948A1

公开(公告)日：2019-06-27

申请号：US15980456

申请日：2018-05-15

Applicant: SK hynix Inc. ,  Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Inchang CHOI

IPC: H04N5/359 ,  H04N5/232 ,  G06T5/00 ,  H04N9/64 ,  H04N5/235

Abstract: An HDR imaging apparatus include: a deinterlacing circuit configured to generate a high-exposure Bayer frame and low-exposure Bayer frame by deinterlacing an interlace Bayer raw frame in which a high-exposure region and low-exposure region are interlaced; a demosaicing circuit configured to convert the high-exposure Bayer frame and the low-exposure Bayer frame into a high-exposure RGB frame and low-exposure RGB frame, respectively; a reconstructing circuit configured to remove interlace artifacts and noise from the high-exposure RGB frame and the low-exposure RGB frame, using joint dictionaries generated through joint dictionary learning on training data sets each containing a plurality of bases, but the corresponding bases have different values; and an HDR generation circuit configured to generate an HDR image frame by combining the high-exposure RGB frame and the low-exposure RGB frame from which interlace artifacts and noise were removed by the reconstructing circuit.

公开(公告)号：US20190096049A1

公开(公告)日：2019-03-28

申请号：US16127014

申请日：2018-09-10

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Inchang CHOI

IPC: G06T5/50 ,  G06N7/08 ,  G06N3/08

Abstract: A method and an apparatus for reconstructing a hyperspectral image using artificial intelligence are provided. The method includes receiving an encoded sensor input for an image and reconstructing a hyperspectral image of the image for the encoded sensor input based on a previously generated nonlinear learning model.

公开(公告)号：US20250148706A1

公开(公告)日：2025-05-08

申请号：US18509771

申请日：2023-11-15

Applicant: Korea Advanced Institute of Science and Technology ,  MIRTEC Co., Ltd.

Inventor： Min Hyuk KIM ,  Hyeongjun CHO

IPC: G06T17/00 ,  G06T7/80

Abstract: Disclosed is a three-dimensional (3D) calibration method and device for multi-view phase shift profilometry. A 3D calibration method for multi-view phase shift profilometry, performed by a computer device, according to an example embodiment may include acquiring a phase that is data required for 3D reconstruction from parameters of at least one camera and a projector based on a phase measuring profilometry (PMP) method; defining a phase-to-depth function for each camera-and-projector combination and performing calibration of optimizing the parameters of the camera and the projector; and acquiring a point cloud that includes depth information using the optimized parameters of the camera and the projector.

公开(公告)号：US20230016057A1

公开(公告)日：2023-01-19

申请号：US17857444

申请日：2022-07-05

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Mustafa Berk YALDIZ ,  Andreas MEULEMAN

IPC: G06V10/22 ,  G06V10/774 ,  G06T15/50 ,  G06T15/80

Abstract: The inventive concept relate to a technology, which recognizes widely deformable markers with high accuracy in an end-to-end manner of message encoding and decoding, and which generates and recognizes deformable fiducial markers based on artificial intelligence, and includes generating, by a marker generator, a unique marker pattern as a fiducial marker in an input binary message, rendering, by an imaging simulator, an image by generating a training dataset of a realistic scene image with the generated fiducial marker, and training a marker detector with the rendered image.

公开(公告)号：US20180045568A1

公开(公告)日：2018-02-15

申请号：US15637884

申请日：2017-06-29

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Min Hyuk KIM ,  Daniel JEON

IPC: G01J3/28 ,  H01L27/146 ,  G01J1/04 ,  G01J3/02 ,  G01J3/18

CPC classification number: G01J3/2823 ,  G01J1/0411 ,  G01J1/0474 ,  G01J3/0205 ,  G01J3/0208 ,  G01J3/021 ,  G01J3/0229 ,  G01J3/0291 ,  G01J3/14 ,  G01J3/18 ,  G01J3/2846 ,  G01J2003/2826 ,  H01L27/14625

Abstract: A method and a system for acquiring a hyperspectral image by using a kaleidoscope are provided. The method includes copying an input image to generate a specific number of images, generating coded-aperture passed images corresponding to the images by using at least one coded aperture, and acquiring a hyperspectral image for the input image based on the coded-aperture passed images.