Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets

Matthew Brown, D G Lowe

Research output: Contribution to conferencePaperpeer-review

199 Citations (Scopus)

Abstract

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.
Original languageEnglish
Pages56-63
Number of pages8
DOIs
Publication statusPublished - Jun 2005
Event3DIM 2005: Fifth International Conference on 3-D Digital Imaging and Modeling, 2005 - Ottawa, Canada
Duration: 13 Jun 200516 Jun 2005

Conference

Conference3DIM 2005: Fifth International Conference on 3-D Digital Imaging and Modeling, 2005
CountryCanada
CityOttawa
Period13/06/0516/06/05

Fingerprint Dive into the research topics of 'Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets'. Together they form a unique fingerprint.

Cite this