Camera calibration from two shadow trajectories

被引:0
作者
Lu, Fei [1 ]
Cao, Xiaochun [1 ]
Shen, Yuping [1 ]
Foroosh, Hassan [1 ]
机构
[1] Univ Cent Florida, Computat Imaging Lab, Orlando, FL 32816 USA
来源
18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS | 2006年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce an efficient method for recovering the camera parameters automatically from the cast shadows of two 3D points observed over time. Compared to previous related work, our method has less restrictions in the sense that object-to-shadow correspondences do not have to be available in the image. We demonstrate how the horizon line may be recovered from only shadow points, and how the camera intrinsic and extrinsic parameters are determined using the pole-polar relationship and minimizing the algebraic distance of the principal point. The approach is fully validated on both synthetic and real data, and tested against various sources of error We finally present an application to metrology from shadows only - i.e. when the object is not visible in the image.
引用
收藏
页码:1 / +
页数:2
相关论文
共 11 条
[1]  
Antone M, 2004, IEEE SYS MAN CYBERN, P3040
[2]  
Cao XC, 2005, PROC CVPR IEEE, P918
[3]  
Collins R. T., 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), P528, DOI 10.1109/CVPR.1999.786988
[4]  
Comaniciu D, 2000, PROC CVPR IEEE, P142, DOI 10.1109/CVPR.2000.854761
[5]  
FAUGERAS OD, 1993, COMPUTER VISION GEOM
[6]  
Hartley R., 2000, MULTIPLE VIEW GEOMET
[7]  
HARTLEY RI, 1994, P ECCV, P471
[8]  
Krahnstoever N, 2005, IEEE I CONF COMP VIS, P1858
[9]  
Lv FJ, 2002, INT C PATT RECOG, P562, DOI 10.1109/ICPR.2002.1044793
[10]  
TSAI RY, 1987, IEEE T ROBOTIC AUTOM, V3, P323, DOI 10.1109/JRA.1987.1087109