Conversion system of monocular image sequence to stereo using motion parallax

被引:25
|
作者
Matsumoto, Y
Terasaki, H
Sugimoto, K
Arakawa, T
机构
来源
STEREOSCOPIC DISPLAYS AND VIRTUAL REALITY SYSTEMS IV | 1997年 / 3012卷
关键词
motion parallax; stereo image generation; computer vision; structure from motion;
D O I
10.1117/12.274446
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A three-dimensional reconstruction system - the 3DR system - has been developed. The main feature of the 3DR system is that it converts monocular image sequences to stereoscopic ones. This provides the following advantages: a) Stereoscopic images can be reproduced even from films taken in the past. b) A compact SD-scene capturing system using a monocular camera is realized. The key 3DR technology is depth sensing based on motion parallax. A novel technique for motion analysis is proposed where, according to classification of motion vectors using the stability and collinearity, an iterative operation is performed to obtain an accurate solution. Preliminary evaluations have shown that not only was the motion parallax analyzed very accurately but also stereoscopic images of high quality were generated.
引用
收藏
页码:108 / 115
页数:8
相关论文
共 50 条
  • [41] RIGID MOTION AND STRUCTURE FROM SEVERAL SETS OF PARALLEL LINES IN A MONOCULAR IMAGE SEQUENCE
    OPEI, SC
    LIOU, LG
    PATTERN RECOGNITION, 1994, 27 (11) : 1475 - 1491
  • [42] Optimal motion parameters and structures estimation of a rigid object from a monocular image sequence
    Ouyang, GH
    Sun, JX
    WAng, XH
    Li, H
    Zhong, S
    ULTRAHIGH- AND HIGH-SPEED PHOTOGRAPHY AND IMAGE-BASED MOTION MEASUREMENT, 1997, 3173 : 395 - 406
  • [43] Importance of Visual Information at Change in Motion Direction on Depth Perception From Monocular Motion Parallax
    Mizushina, Haruki
    Kanayama, Ippei
    Masuda, Yuki
    Suyama, Shiro
    IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2020, 56 (05) : 5637 - 5644
  • [44] PMCN: Parallax-motion collaboration network for stereo video dehazing
    Wu, Chang
    He, Gang
    Zhao, Wanlin
    Lai, Xinquan
    Li, Yunsong
    KNOWLEDGE-BASED SYSTEMS, 2024, 305
  • [45] A Method to Introduce & Evaluate Motion Parallax with Stereo for Medical AR/MR
    Kalia, Megha
    Navab, Nassir
    Fels, Sidney
    Salcudean, Tim
    2019 26TH IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES (VR), 2019, : 1755 - 1759
  • [46] How to realize a natural image reproduction using stereoscopic displays with motion parallax
    Runde, D
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2000, 10 (03) : 376 - 386
  • [47] Joint estimation of depth and motion from a monocular endoscopy image sequence using a multi-loss rebalancing network
    Liu, Shiyuan
    Fan, Jingfan
    Song, Dengpan
    Fu, Tianyu
    Lin, Yucong
    Xiao, Deqiang
    Song, Hong
    Wang, Yongtian
    Yang, Jian
    BIOMEDICAL OPTICS EXPRESS, 2022, 13 (05) : 2707 - 2727
  • [48] MOTION PARALLAX CUES IMPROVE MONOCULAR AND BINOCULAR EQUI-DISTANCE JUDGMENTS
    PRESTRUDE, AM
    DECICCO, M
    BULLETIN OF THE PSYCHONOMIC SOCIETY, 1977, 10 (04) : 250 - 250
  • [49] Flow-Motion and Depth Network for Monocular Stereo and Beyond
    Wang, Kaixuan
    Shen, Shaojie
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2020, 5 (02): : 3307 - 3314
  • [50] Effective displaying methods of monocular motion parallax for more realistic depth perception
    Mizushina, Haruki
    Oko, Kazuya
    Masuda, Yuki
    Suyama, Shiro
    THREE-DIMENSIONAL IMAGING, VISUALIZATION, AND DISPLAY 2020, 2020, 11402