The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
비디오 데이터로부터 사실적인 3D 장면을 구성하는 것은 컴퓨터 비전, 이미지 처리 및 컴퓨터 그래픽 분야에서 활발하고 경쟁이 치열한 연구 분야입니다. 이 문서에서는 이 분야의 최근 작업을 다루고 있습니다. 대부분의 3D 장면 구성 방법과 달리 우리는 비디오 캠의 전진 동작으로 비디오 시퀀스에서 가상 환경 생성을 고려합니다. 각 프레임은 모션 매개변수를 추정하기 위해 Levenberg-Marquardt 반복 알고리즘을 사용하여 그에 따라 등록되는 하위 이미지로 분해됩니다. 등록된 하위 이미지는 그에 따라 함께 붙여져 의사 3D 공간을 형성합니다. 위치와 방향을 제어함으로써 가상 카메라는 이 가상 공간을 통과하여 새로운 2D 뷰를 생성하여 몰입감 있는 인상을 얻을 수 있습니다. 가상 카메라가 가상 환경 깊숙이 들어가더라도 상대적으로 높은 해상도를 유지하면서 새로운 시각을 얻을 수 있습니다.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Xiaohua ZHANG, Hiroki TAKAHASHI, Masayuki NAKAJIMA, "Creating Virtual Environment Based on Video Data with Forward Motion" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 4, pp. 931-936, April 2000, doi: .
Abstract: The construction of photo-realistic 3D scenes from video data is an active and competitive area of research in the fields of computer vision, image processing and computer graphics. In this paper we address our recent work in this area. Unlike most methods of 3D scene construction, we consider the generation of virtual environments from video sequence with a video-cam's forward motion. Each frame is decomposed into sub-images, which are registered correspondingly using the Levenberg-Marquardt iterative algorithm to estimate motion parameters. The registered sub-images are correspondingly pasted together to form a pseudo-3D space. By controlling the position and direction, the virtual camera can walk through this virtual space to generate novel 2D views to acquire an immersive impression. Even if the virtual camera goes deep into this virtual environment, it can still obtain a novel view while maintaining relatively high resolution.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_4_931/_p
부
@ARTICLE{e83-d_4_931,
author={Xiaohua ZHANG, Hiroki TAKAHASHI, Masayuki NAKAJIMA, },
journal={IEICE TRANSACTIONS on Information},
title={Creating Virtual Environment Based on Video Data with Forward Motion},
year={2000},
volume={E83-D},
number={4},
pages={931-936},
abstract={The construction of photo-realistic 3D scenes from video data is an active and competitive area of research in the fields of computer vision, image processing and computer graphics. In this paper we address our recent work in this area. Unlike most methods of 3D scene construction, we consider the generation of virtual environments from video sequence with a video-cam's forward motion. Each frame is decomposed into sub-images, which are registered correspondingly using the Levenberg-Marquardt iterative algorithm to estimate motion parameters. The registered sub-images are correspondingly pasted together to form a pseudo-3D space. By controlling the position and direction, the virtual camera can walk through this virtual space to generate novel 2D views to acquire an immersive impression. Even if the virtual camera goes deep into this virtual environment, it can still obtain a novel view while maintaining relatively high resolution.},
keywords={},
doi={},
ISSN={},
month={April},}
부
TY - JOUR
TI - Creating Virtual Environment Based on Video Data with Forward Motion
T2 - IEICE TRANSACTIONS on Information
SP - 931
EP - 936
AU - Xiaohua ZHANG
AU - Hiroki TAKAHASHI
AU - Masayuki NAKAJIMA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2000
AB - The construction of photo-realistic 3D scenes from video data is an active and competitive area of research in the fields of computer vision, image processing and computer graphics. In this paper we address our recent work in this area. Unlike most methods of 3D scene construction, we consider the generation of virtual environments from video sequence with a video-cam's forward motion. Each frame is decomposed into sub-images, which are registered correspondingly using the Levenberg-Marquardt iterative algorithm to estimate motion parameters. The registered sub-images are correspondingly pasted together to form a pseudo-3D space. By controlling the position and direction, the virtual camera can walk through this virtual space to generate novel 2D views to acquire an immersive impression. Even if the virtual camera goes deep into this virtual environment, it can still obtain a novel view while maintaining relatively high resolution.
ER -