LEARNING TO TRACK THE VISUAL-MOTION OF CONTOURS

被引：84

作者：

BLAKE, A

ISARD, M

REYNARD, D

机构：

[1] Department of Engineering Science, University of Oxford, Oxford, OX1 3PJ, Parks Road

来源：

ARTIFICIAL INTELLIGENCE | 1995年 / 78卷 / 1-2期

关键词：

D O I：

10.1016/0004-3702(95)00032-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A development of a method for tracking visual contours is described. Given an ''untrained'' tracker, a training motion of an object can be observed over some extended time and stored as an image sequence. The image sequence is used to learn parameters in a stochastic differential equation model. These are used, in turn, to build a tracker whose predictor imitates the motion in the training set. Tests show that the resulting trackers can be markedly tuned to desired curve shapes and classes of motions.

引用

页码：179 / 212

页数：34

共 38 条

[1]

Astrom K., 1997, COMPUTER CONTROLLED, V3

[2]

Astrom K. J., 1970, INTRO STOCHASTIC CON

[3]

AYACHE N, 1992, ACTIVE VISION, P285

[4] VISUALLY CONTROLLED GRAPHICS [J].

AZARBAYEJANI, A ;

STARNER, T ;

HOROWITZ, B ;

PENTLAND, A .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (06) :602-605

[5]

BARNETT S, 1990, MATRICES METHODS APP

[6]

BARSHALOM Y, 1988, TRACKING DATA ASS

[7]

Bartels R.H., 1987, INTRO SPLINES USE CO

[8]

BAUMBERG A, 1994, 3 EUR C COMP VIS, P299

[9]

BENNETT AD, 1991, P BRIT MACHINE VISIO, P233

[10]

Blake A., 1993, [1993] Proceedings Fourth International Conference on Computer Vision, P66, DOI 10.1109/ICCV.1993.378234

← 1 2 3 4 →