Affine propagation for surface reconstruction in wide baseline stereo

被引：8

作者：

Megyesi, Z ^{[1
]}

Chetverikov, D ^{[1
]}

机构：

[1] Comp & Automat Res Inst, Budapest, Hungary

来源：

PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4 | 2004年

关键词：

D O I：

10.1109/ICPR.2004.1333709

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The problem of dense matching in wide baseline stereo is considered It is assumed that the scene is formed by piecewise-smooth, Lambertian, textured surfaces and that rectified images of the scene are available. We present a novel dense matching algorithm that accounts for local affine distortion and propagates the best matching affine parameters on each surface until a surface discontinuity is reached Disparity maps and projective reconstructions for real-world wide baseline stereo images are shown.

引用

页码：76 / 79

页数：4

共 10 条

[1]

[Anonymous], 1993, Digital Image Processing Algorithms

[2]

Baumberg A, 2000, PROC CVPR IEEE, P774, DOI 10.1109/CVPR.2000.855899

[3]

BIRCHFIELD S, 1999, P ICCV

[4]

Hartley R., 2000, MULTIPLE VIEW GEOMET

[5] Improvements in real-time correlation-based stereo vision [J].

Hirschmüller, H .

IEEE WORKSHOP ON STEREO AND MULTI-BASELINE VISION, PROCEEDINGS, 2001, :141-148

[6]

Matas J., 2002, Electronic Proceedings of the 13th British Machine Vision Conference, P384

[7] REGION-GROWING ALGORITHM FOR MATCHING OF TERRAIN IMAGES [J].

OTTO, GP ;

CHAU, TKW .

IMAGE AND VISION COMPUTING, 1989, 7 (02) :83-94

[8] A taxonomy and evaluation of dense two-frame stereo correspondence algorithms [J].

Scharstein, D ;

Szeliski, R .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2002, 47 (1-3) :7-42

[9]

Shi J., 1994, P IEEE C COMP VIS PA

[10]

Trucco E., 1998, INTRO TECHNIQUES 3D

← 1 →