Models from Image Triplets using Epipolar Gradient Features

Vincent, É.; Laganière, R.

Models from Image Triplets using Epipolar Gradient Features

Files

20_paper12.new.pdf (1.48 MB)

Date

2003

Authors

Vincent, É.
Laganière, R.

Publisher

The Eurographics Association

Abstract

In an application where sparse matching of feature points is used towards fast scene reconstruction, the choice of the type of features to be matched has an important impact on the quality of the resulting model. In this work, a method is presented for quickly and reliably selecting and matching points from three views of a scene. The selected points are based on epipolar gradients, and consist in stable image features relevant to reconstruction. Then, the selected points are matched using edge transfer, a measure of geometric consistency for point triplets and the edges on which they lie. This matching scheme is invariant to image deformations due to changes in viewpoint. Models drawn from matches obtained by the proposed technique are shown to demonstrate its usefulness.

        @inproceedings{10.2312:vvg.20031020
,
booktitle = {Vision, Video, and Graphics (VVG) 2003
},
editor = {Peter Hall and Philip Willis
},
title = {{Models from Image Triplets using Epipolar Gradient Features
}},
author = {Vincent, É. and 
Laganière, R.
},
year = {2003
},
publisher = {The Eurographics Association
},
ISBN = {3-905673-54-1
},
DOI = {10.2312/vvg.20031020
}
}