公开(公告)号：US20250131587A1

公开(公告)日：2025-04-24

申请号：US18924898

申请日：2024-10-23

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Ji-Youn LIM ,  Won-Joo PARK ,  Jeong-Woo SON ,  Alex LEE

IPC: G06T7/73 ,  G06T7/11

Abstract: Disclosed herein are an asset creation method using a covariance matrix-based parallel network and an apparatus for the same. The asset creation method includes simultaneously performing segmentation and position information identification on a target object to be assetized from a video received from a user terminal based on a parallel network including a three-dimensional (3D) semantic segmentation network and a Long Short-Term Memory (LSTM) network, and generating a 3D video feature of the target object from results of the segmentation and the position information identification based on a covariance matrix, and creating an asset in conformity with the 3D video feature.

公开(公告)号：US20220004773A1

公开(公告)日：2022-01-06

申请号：US17166444

申请日：2021-02-03

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jeong-Woo SON ,  Chang-Uk KWAK ,  Sun-Joong KIM ,  Alex LEE ,  Min-Ho HAN ,  Gyeong-June HAHM

IPC: G06K9/00 ,  G06T7/70 ,  G06K9/46 ,  G06K9/62 ,  G06T7/00 ,  G11B27/34 ,  G11B27/10 ,  G06N3/04 ,  G06N3/08 ,  G06F16/735 ,  G06F16/738

Abstract: Disclosed herein is an apparatus for analyzing a video shot. The apparatus includes at least one program, memory in which the program is recorded, and a processor for executing the program. The program may include a frame extraction unit for extracting at least one frame from a video shot, a shot composition and camera position recognition unit for predicting shot composition and a camera position for the extracted at least one frame based on a previously trained shot composition recognition model, a place and time information extraction unit for predicting a shot location and a shot time for the extracted at least one frame based on previously trained shot location recognition model and shot time recognition model, and an information combination unit for combining pieces of information, respectively predicted for the at least one frame, for each video shot and tagging the video shot with the combined pieces of information.