公开(公告)号：US20220270276A1

公开(公告)日：2022-08-25

申请号：US17675415

申请日：2022-02-18

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Han-Shin LIM

IPC: G06T7/55 ,  G06T17/20

Abstract: Disclosed herein is a method for generating a depth map from multi-view images, the method including receiving multi-view images and parameters thereof; generating an initial depth map, an initial normal map, and an initial reliability map for the multi-view images; performing selection of multiple initial vertices and triangulation based on the initial depth map and the initial normal map and generating depth values and normal values for the result of triangulation; performing regularization based on triangulation, selecting additional vertices in the initial depth map, and generating additional depth values and additional normal values based on the additional vertices and regularization; and refining the initial depth map into a refined depth map by replacing depth values and normal values having reliability below a preset level in the initial depth map and the initial normal map with the additional depth values and the additional normal values.

公开(公告)号：US20220166976A1

公开(公告)日：2022-05-26

申请号：US17534770

申请日：2021-11-24

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyon-Gon CHOO ,  Hee-Kyung LEE ,  Han-Shin LIM ,  Jeong-Il SEO ,  Won-Sik CHEONG

IPC: H04N19/119 ,  G06T7/11 ,  G06T7/90 ,  G06T7/40 ,  H04N19/136 ,  H04N19/176 ,  H04N19/186 ,  H04N19/80 ,  H04N19/46

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a segmentation map. A feature vector for an image may be extracted using a segmentation map. The image may be encoded using the segmentation map and the feature vector. An output stream from an encoding apparatus may include a video stream and a feature stream. An input stream to a decoding apparatus may include a video stream and a feature stream. The image may be reconstructed using a reconstructed segmentation map and a reconstructed feature vector.

公开(公告)号：US20220301181A1

公开(公告)日：2022-09-22

申请号：US17697463

申请日：2022-03-17

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  KONKUK UNIVERSITY INDUSTRIAL COOPERATION CORP

Inventor： Kyoung-Ro YOON ,  Han-Shin LIM ,  Hyon-Gon CHOO ,  Shin KIM ,  Ye-Gi LEE

IPC: G06T7/194 ,  G06V10/20 ,  G06V10/28 ,  G06T9/00

Abstract: Disclosed herein is a method for compressing an image for machine vision, the method including detecting objects in an input image using an object detection network, generating a foreground image including bounding boxes corresponding to the objects and a background image, which is an image acquired by excluding the bounding boxes from the input image, encoding the foreground image and the background image, and decoding the encoded foreground image and the encoded background image.

公开(公告)号：US20220398699A1

公开(公告)日：2022-12-15

申请号：US17839181

申请日：2022-06-13

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hyon-Gon CHOO ,  Jeong-Il SEO ,  Jin-Young LEE ,  Hee-Kyung LEE ,  Han-Shin LIM ,  Won-Sik CHEONG

IPC: G06T5/00

Abstract: Disclosed herein are an image processing method and apparatus for machine vision. The image processing method for machine vision includes generating an image with machine-unrecognizable distortion based on an input image, and encoding the image with machine-unrecognizable distortion.