Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets
- 1 June 2005
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
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 allKeywords
This publication has 11 references indexed in Scilit:
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- 3D object modeling and recognition using affine-invariant patches and multi-view spatial constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognising panoramasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Shape indexing using approximate nearest-neighbour search in high-dimensional spacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reliable feature matching across widely separated viewsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object recognition from local scale-invariant featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Local grayvalue invariants for image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997