Unsupervised 3D object recognition and reconstruction in unordered datasets

被引：131

作者：

Brown, M ^{[1
]}

Lowe, DG ^{[1
]}

机构：

[1] Univ British Columbia, Dept Comp Sci, Vancouver, BC V5Z 1M9, Canada

来源：

FIFTH INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS | 2005年

关键词：

D O I：

10.1109/3DIM.2005.81

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

This paper presents a system for fully automatic recognition and reconstruction of 3D objects in image databases. We pose the object recognition problem as one of finding consistent matches between all images, subject to the constraint that the images were taken from a perspective camera. We assume that the objects or scenes are rigid. For each image we associate a camera matrix, which is parameterised by rotation, translation and focal length. We use invariant local features to find matches between all images, and the RANSAC algorithm to find those that are consistent with the fundamental matrix. Objects are recognised as subsets of matching images. We then solve for the structure and motion of each object, using a sparse bundle adjustment algorithm. Our results demonstrate that it is possible to recognise and reconstruct 3D objects from an unordered image database with no user input at all.

引用

页码：56 / +

页数：2

共 16 条

[1]

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

[2] Shape indexing using approximate nearest-neighbour search in high-dimensional spaces [J].

Beis, JS ;

Lowe, DG .

1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :1000-1006

[3]

Brown M, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P1218

[4]

Brown M., 2005, P INT C COMP VIS PAT

[5]

Fergus R, 2003, P INT C COMP VIS PAT

[6]

Hartley R., 2000, MULTIPLE VIEW GEOMET

[7]

Lowe D.G., 1999, P IEEE INT C COMP VI, P1150, DOI DOI 10.1109/ICCV.1999.790410

[8] Distinctive image features from scale-invariant keypoints [J].

Lowe, DG .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110

[9] Robust wide-baseline stereo from maximally stable extremal regions [J].

Matas, J ;

Chum, O ;

Urban, M ;

Pajdla, T .

IMAGE AND VISION COMPUTING, 2004, 22 (10) :761-767

[10]

MIKOLAJCZYK K, 2002, P EUR C COMP VIS

← 1 2 →