3D Model Acquisition from Extended Image Sequences
Abstract
A method for matching image primitives through a sequence is described, for the purpose of acquiring 3D geometric models. The method includes a novel robust estimator of the trifocal tensor, based on a minimum number of token correspondences across an image triplet; and a novel tracking algorithm in which corners and line segments are matched over image triplets in an integrated framework. The matching techniques are both robust (detecting and discarding mismatches) and fully automatic. The matched tokens are used to compute 3D structure, which is initialised as it appears and then recursively updated over time. The approach is uncalibrated — camera internal parameters and camera motion are not known or required. Experimental results are provided for a variety of scenes, including outdoor scenes taken with a hand-held camcorder. Quantitative statistics are included to assess the matching performance, and renderings of the 3D structure enable a qualitative assessment of the results.
Cite
Text
Beardsley et al. "3D Model Acquisition from Extended Image Sequences." European Conference on Computer Vision, 1996. doi:10.1007/3-540-61123-1_181Markdown
[Beardsley et al. "3D Model Acquisition from Extended Image Sequences." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/beardsley1996eccv-d/) doi:10.1007/3-540-61123-1_181BibTeX
@inproceedings{beardsley1996eccv-d,
title = {{3D Model Acquisition from Extended Image Sequences}},
author = {Beardsley, Paul A. and Torr, Philip H. S. and Zisserman, Andrew},
booktitle = {European Conference on Computer Vision},
year = {1996},
pages = {683-695},
doi = {10.1007/3-540-61123-1_181},
url = {https://mlanthology.org/eccv/1996/beardsley1996eccv-d/}
}