VISION AND LIES APPROACH TO INVARIANCE

被引：59

作者：

VANGOOL, L

MOONS, T

PAUWELS, E

OOSTERLINCK, A

机构：

[1] Katholieke Universiteit Leuven, ESAT, B-3001 Leuven

来源：

IMAGE AND VISION COMPUTING | 1995年 / 13卷 / 04期

关键词：

INVARIANCE; LIE THEORY; RECOGNITION; FEATURE EXTRACTION;

D O I：

10.1016/0262-8856(95)99715-D

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The application of invariance theory has gained a. renewed interest in the computer vision community. Recent results show that it offers a strong, unifying framework that helps in tackling problems such as calibration-less vision, efficient matching, shape-from-motion, grouping, and several other problems considered crucial to intelligent vision. Nonetheless, a systematic approach to the problem of extracting invariants is far from trivial. This paper describes one such approach, the theory of Lie groups. After a concise and non-rigorous account on the method itself, typical problems that arise in vision are discussed. For each of these problems, one or more relevant examples are given.

引用

页码：259 / 277

页数：19

共 26 条

[1]

Bruckstein, Netravali, Differential invariants of planar curves and recognizing partially occluded shapes, Visual Form, pp. 89-98, (1992)

[2]

Faugeras, What can be seen in three dimensions with an uncalibrated stereo rig, Proc. 2nd Euro. Conf. Comput. Vision, pp. 563-578, (1992)

[3]

Hartley, Euclidean reconstruction from uncalibrated views, Appl. Invariance in Comput. Vision, pp. 237-256, (1994)

[4]

Huttenlocher, Ullman, Object recognition using allignment, Proc. Int. Conf. Comput. Vision, pp. 496-500, (1987)

[5]

Kempenaers, Van Gool, Oosterlinck, Semi-differential invariants algebraic-differential hybrids, SPIE Proc. Hybrid Image and Signal Processing III, pp. 41-52, (1992)

[6]

Koenderink, van Doom, Affine structure from motion, J. Opt. Soc. Am. A, 8, pp. 377-385, (1991)

[7]

Lamdan, Schwartz, Wolfson, On recognition of 3D objects from 2D images, Proc. Int. Conf. Robotics Automation, pp. 1407-1413, (1988)

[8]

Maybank, Classification based on the cross ratio, Appl. Invariance in Comput. Vision, pp. 458-472, (1994)

[9]

Mohr, Veillon, Quan, Relative 3D reconstruction using multiple uncalibrated images, Proc. Conf. Comput. Vision Patt. Recogn., pp. 543-548, (1993)

[10]

Moons, Van Gool, Van Diest, Pauwels, Affine reconstruction from perspective image pairs, Appl. Invariance in Comput. Vision, pp. 297-316, (1994)

← 1 2 3 →