Trifocal motion modeling for object-based video compression and manipulation

作者: Zhaohui Sun , A.M. Tekalp

DOI: 10.1109/76.718512

关键词:

摘要: Following an overview of two-dimensional (2-D) parametric motion models commonly used in video manipulation and compression, we introduce trifocal transfer, which is image-based scene representation computer vision, as a compensation method that uses three frames at time to implicitly capture camera/scene depth. Trifocal transfer requires tensor computed by matching image features across views dense correspondence between two the views. We propose approximating model order apply for object-based compression background mosaic generation. Backward, forward, bidirectional methods based on are presented. The performance proposed approaches using has been compared with various other methods, such motion, block global affine transform several sequences. Finally, synthesis implemented within MPEG-4 Video Verification Model (VM), results those standard VM. Experimental show superior when there depth variation camera translation.

参考文章(30)
A. Murat Tekalp, Digital Video Processing ,(1995)
Amnon Shashua, Trilinear Tensor: The Fundamental Construct of Multiple-view Geometry and Its Applications Lecture Notes in Computer Science. pp. 190- 206 ,(1997) , 10.1007/BFB0017868
Richard I Hartley, None, Lines and Points in Three Views and the Trifocal Tensor International Journal of Computer Vision. ,vol. 22, pp. 125- 140 ,(1997) , 10.1023/A:1007936012022
Paul Beardsley, Phil Torr, Andrew Zisserman, 3D Model Acquisition from Extended Image Sequences european conference on computer vision. pp. 683- 695 ,(1996) , 10.1007/3-540-61123-1_181
Theodoros Evgeniou, Image Based Rendering Using Algebraic Techniques Massachusetts Institute of Technology. ,(1996)
H. C. Longuet-Higgins, A computer algorithm for reconstructing a scene from two projections Nature. ,vol. 293, pp. 61- 62 ,(1987) , 10.1038/293133A0
H.S. Sawhney, Simplifying multiple motion and structure analysis using planar parallax and image warping Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects. pp. 104- 109 ,(1994) , 10.1109/MNRAO.1994.346248
H.S. Sawhney, S. Ayer, M. Gorkani, Model-based 2D&3D dominant motion estimation for mosaicing and video representation international conference on computer vision. pp. 583- 590 ,(1995) , 10.1109/ICCV.1995.466886
Michal Irani, P. Anandan, Jim Bergen, Rakesh Kumar, Steve Hsu, Efficient representations of video sequences and their applications Signal Processing-image Communication. ,vol. 8, pp. 327- 351 ,(1996) , 10.1016/0923-5965(95)00055-0
Olivier Faugeras, Three-dimensional computer vision: a geometric viewpoint computer aided architectural design futures. ,vol. 29, ,(1993)