OALib Journal期刊
ISSN: 2333-9721
费用:99美元
|
|
|
由抖动图象序列建立自然环境三维真实感全景模型
DOI: 10.11834/jig.199809219
Keywords: 基于图象的VR,图象稳定,外极面图象,全景图象,分层表示
Abstract:
由真实环境中的现场图象进行三维环境建模是目前国际上研究的热点问题。本文依据合理的运动模型,提出和实现了由包含抖动的摄像机运动下的图象序列建立3D环境全景模型的两步法。首先通过运动滤波和运动分解获得运动稳定的图象序列,然后采用无特征提取的时空纹理方向精确估计、深度边界确定和遮挡恢复算法,建立全局自然景物的真实感三维环境模型。提出了2种三维全景图象的表示方法,即非阵列方式深度分层区域表示和阵列方式的深度分层布景表示,可用于机器人全局定位的自然路标提取和真实环境虚拟再现的图象合成。该研究推广和结合了外极面图象的
References
[1] | Szeliski R.Image mosaicing for tele-reality application.Proc.2nd IEEE Workshop on Application of Computer Vision,1994,44-53.
|
[2] | Wang J.Adelson E H,Representation moving images with layers.IEEE Trans.on Image Processing.1994,3(5):625-638.
|
[3] | Baker H H,Bolles RC.Generalizing epipolar-plane image analysis on the spatio-temporal surface.In:Proc CVPR,1988:2-9.
|
[4] | Costeira J.Kanade T.A multi-body factorization method for motion analysis.I:Proc.ICCV\\'95,:10-1076.
|
[5] | Dalmia A K,Trivedi M.High speed extraction fo 3D structure of selectable quality using a translating camera.CVIU,1996.64(1):97-110.
|
[6] | Irani M.Ananda P,Hsu S.Mosaic based representation of video sequence and their applications.In:Proc ICCV\\'95,605-611.
|
[7] | 杨雨东 徐光You.2.5维帧间运动估计方法[J].清华大学学报:自然科学版,1997,37(9):.
|
[8] | Kanade T,Rander P,Narayanan P J.Virtualized reality: Consructing virtual worlds from real scenes.IEEE Multimedia,1997:34-47.
|
[9] | Zheng J Y,Barth M,Tsuji S.Panoramic representation of scenes for route understanding.In:Proc.IEEE 10th ICPR,1990:161-167.
|
[10] | Sawhney H S,Ayer S.Compact representation of videos through dominant and multiple motion estimation.IEEE Trans.PAMJ.1996,18(8):814-830.
|
[11] | Ishiguro H,Yamamoto M.Tsuji S.Omni-directional stereo for making global map.In:Proc.ICCV-90.
|
[12] | Tomasi C,Kanade T,Shape and motion from image streams under orthography:A factorization method.Int CV.9,1992,137-154.
|
[13] | Murray D W.Recovering range using virtual multicamera stereo.CVIU,1995.61(2):285-291.
|
[14] | 朱志刚.[D].北京:清华大学计算机系,1997,6.
|
Full-Text
|
|
Contact Us
service@oalib.com QQ:3279437679 
WhatsApp +8615387084133
|
|