Preemptive RANSAC for live structure and motion estimation

被引：224

作者：

Nistér, D ^{[1
]}

机构：

[1] Sarnoff Corp, Princeton, NJ 08530 USA

来源：

MACHINE VISION AND APPLICATIONS | 2005年 / 16卷 / 05期

关键词：

structure from motion; real-time; robust estimation; 3D-reconstruction; ego-motion;

D O I：

10.1007/s00138-005-0006-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A system capable of performing robust live ego-motion estimation for perspective cameras is presented. The system is powered by random sample consensus with preemptive scoring of the motion hypotheses. A general statement of the problem of efficient preemptive scoring is given. Then a theoretical investigation of preemptive scoring under a simple inlier-outlier model is performed. A practical preemption scheme is proposed and it is shown that the preemption is powerful enough to enable robust live structure and motion estimation.

引用

页码：321 / 329

页数：9

共 24 条

[1] [Anonymous], 2000, LNCS, DOI DOI 10.1007/3-540-44480-7
[2] Sequential updating of projective and affine structure from motion
Beardsley, PA
Zisserman, A
Murray, DW
[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 23 (03) : 235 - 259
[3] Bjorkmann M., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P234, DOI 10.1109/ICCV.1999.791225
[4] CHIUSO A, 2000, LECT NOTES COMPUTER, V1842, P735
[5] Chum O., 2002, Electronic Proceedings of the 13th British Machine Vision Conference, P623
[6] RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY
FISCHLER, MA
BOLLES, RC
[J]. COMMUNICATIONS OF THE ACM, 1981, 24 (06) : 381 - 395
[7] HARALICK RM, 1994, INT J COMPUT VISION, V13, P331, DOI 10.1007/BF02028352
[8] HARTLEY R, 2002, P 5 AS C COMP VIS ME
[9] Jin HL, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL I, PROCEEDINGS, P684, DOI 10.1109/ICCV.2001.937588
[10] Jin HL, 2000, PROC CVPR IEEE, P778, DOI 10.1109/CVPR.2000.854954

← 1 2 3 →