Extracting structure from optical flow using the fast error search technique

被引:22
作者
Srinivasan, S
机构
[1] Microsoft Corp, Redmond, WA 98052 USA
[2] Univ Maryland, Ctr Automat Res, College Pk, MD 20742 USA
关键词
structure from motion; fast partial search; focus of expansion; optical flow;
D O I
10.1023/A:1008111923880
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a globally optimal and computationally efficient technique for estimating the focus of expansion (FOE) of an optical flow field, using fast partial search. For each candidate location on a discrete sampling of the image area, we generate a linear system of equations for determining the remaining unknowns, viz. rotation and inverse depth. We compute the least squares error of the system without actually solving the equations, to generate an error surface that describes the goodness of fit across the hypotheses. Using Fourier techniques, we prove that given an N x N flow field, the FOE, and subsequently rotation and structure, can be estimated in O(N-2 log N) operations. Since the resulting system is linear, bounded perturbations in the data lead to bounded errors. We support the theoretical development and proof of our technique with experiments on synthetic and real data. Through a series of experiments on synthetic data, we prove the correctness, robustness and operating envelope of our algorithm. We demonstrate the utility of our technique by applying it for detecting obstacles from a monocular sequence of images.
引用
收藏
页码:203 / 230
页数:28
相关论文
共 35 条
[1]   INHERENT AMBIGUITIES IN RECOVERING 3-D MOTION AND STRUCTURE FROM A NOISY FLOW FIELD [J].
ADIV, G .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (05) :477-489
[3]  
ALOIMONOS Y, 1984, IEEE WORKSH COMP VIS, P72
[4]  
[Anonymous], 1993, THESIS MIT
[5]   PERFORMANCE OF OPTICAL-FLOW TECHNIQUES [J].
BARRON, JL ;
FLEET, DJ ;
BEAUCHEMIN, SS .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) :43-77
[6]   PASSIVE NAVIGATION [J].
BRUSS, AR ;
HORN, BKP .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1983, 21 (01) :3-20
[7]   What can projections of flow fields tell us about the visual motion [J].
Fejes, S ;
Davis, LS .
SIXTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, 1998, :979-986
[8]   On the geometry of visual correspondence [J].
Fermuller, C ;
Aloimonos, Y .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 21 (03) :223-247
[9]   QUALITATIVE EGOMOTION [J].
FERMULLER, C ;
ALOIMONOS, Y .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1995, 15 (1-2) :7-29
[10]  
Gibson J. J., 1955, PERCEPTION VISUAL WO