A Closed Form Solution to Segment 3D Motion Using Straight-line Optical Flow

被引：1

作者：

张婧 ^{[1
]}

石繁槐 ^{[2
]}

马文娟 ^{[1
]}

刘允才 ^{[1
]}

机构：

[1] Institute Image Processing and Pattern Recognition, Shanghai Jiaotong University

[2] School of Materials Science and Engineering, Shanghai Jiaotong University

来源：

Journal of Shanghai Jiaotong University | 2008年 / 01期

关键词：

segmentation; optical flow; line; generalized principal component analysis (GPCA);

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

<正>A closed form solution to the problem of segmenting multiple 3D motion models was proposed from straight-line optical flow. It introduced the multibody line optical flow constraint (MLOFC), a polynomial equation relating motion models and line parameters. The motion models can be obtained analytically as the derivative of the MLOFC at the corresponding line measurement, without knowing the motion model associated with that line. Experiments on real and synthetic sequences were also presented.

引用

页码：76 / 80

页数：5

共 4 条

[1] 从二维图像直线光流场求解三维刚体旋转运动参数 [J].

江少锋 ;

陈震 ;

黎明 ;

杨素华 .

南昌航空工业学院学报(自然科学版), 2005, (04) :5-8+19

[2] Motion segmentation of multiple translating objects from line correspondences [J].

Shi, FH ;

Wang, JH ;

Zhang, J ;

Liu, YC .

PATTERN RECOGNITION, 2005, 38 (10) :1775-1778

[3] Geometric motion segmentation and model selection [J].

Torr, PHS .

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 1998, 356 (1740) :1321-1338

[4]

The multibody trifocal tensor: Motion segmentation from 3 perspective views. Hartley R,Vidal R. IEEE Conf Computer Vision and Pattern Recognition . 2004

← 1 →