公开(公告)号：US20250157251A1

公开(公告)日：2025-05-15

申请号：US18941406

申请日：2024-11-08

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ho Won KIM ,  Hye-sun KIM ,  Chang Joon PARK

IPC: G06V40/16 ,  G06V10/774

Abstract: An electronic device for detecting feature information from a face and an operating method of the electronic device are disclosed. The operating method may include: acquiring, via a camera, an input image including a person; setting a normalized virtual camera for generating a normalized image from the input image; generating a normalized image including a perspective projection feature that includes a face of the person based on the normalized virtual camera; inputting the normalized image to an artificial intelligence (AI) model trained to extract feature information of the face; and transforming the feature information of the face output from the AI model into a first coordinate system which is a coordinate system of the camera, using a spatial transformation relationship between the camera and the normalized virtual camera.

公开(公告)号：US20230169741A1

公开(公告)日：2023-06-01

申请号：US17866950

申请日：2022-07-18

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yun Ji BAN ,  Hye-sun KIM

IPC: G06T19/20 ,  G06T17/20 ,  G06T7/11 ,  G06T17/05

CPC classification number: G06T19/20 ,  G06T17/20 ,  G06T7/11 ,  G06T17/05 ,  G06T2219/2008 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20092

Abstract: Disclosed is a separation method including obtaining a mesh model separated into an object unit, based on a segmentation image extracting an object included in an image sequence, updating second label information of the separated mesh model, based on first label information of the segmentation image and a user's input, and updating the separated mesh model, based on the updated second label information, in which an integrated mesh model before being separated into an object unit is generated from the image sequence.

公开(公告)号：US20230162363A1

公开(公告)日：2023-05-25

申请号：US17866710

申请日：2022-07-18

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hye-sun KIM ,  Yun Ji BAN

IPC: G06T7/10 ,  G06T5/00 ,  G06T15/04

CPC classification number: G06T7/10 ,  G06T5/001 ,  G06T15/04

Abstract: Provided is a method of separating a terrain model and an object model from a three-dimensional integrated model and an apparatus for performing the same. A separation method according to various example embodiments includes creating separation information about an integrated model based on a multi-viewpoint image including an object on a terrain, model information of the integrated model obtained by restoring the multi-viewpoint image in three dimensions, and information of an image shooting device shooting the multi-viewpoint image, and separating a terrain model and an object model from the integrated model based on the separation information.

公开(公告)号：US20150229903A1

公开(公告)日：2015-08-13

申请号：US14609876

申请日：2015-01-30

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hye-sun KIM ,  Seung Woo NAM ,  Yun Ji BAN ,  Kyung Ho JANG

IPC: H04N13/00 ,  H04N13/04

CPC classification number: H04N13/261

Abstract: An apparatus for converting a 2D video into a 3D video updates a plurality of segmentation images of a previous frame by using motion information with respect to each frame, applies depth information of each segmentation image of the previous frame to a corresponding segmentation image of a subsequent frame to create a depth map image of each frame, and creates a stereoscopic image of each frame by using the depth map image of each frame.

Abstract translation: 将2D视频转换为3D视频的装置通过使用关于每帧的运动信息来更新先前帧的多个分割图像，将前一帧的每个分割图像的深度信息应用​​于随后的相应分割图像 以创建每个帧的深度图图像，并且通过使用每帧的深度图图像来创建每个帧的立体图像。