Image Quality Assessment for Photo-consistency Evaluation on Planar Classification in Urban Scenes
Marie-Anne Bauda, Sylvie Chambon, Pierre Gurdjos, Vincent Charvillat
2015
Abstract
In the context of semantic segmentation of urban scenes, the calibrated multi-views and the flatness assumption are commonly used to estimate a warped image based on the homography estimation. In order to classify planar and non-planar areas, we propose an evaluation protocol that compares several Image Quality Assessments (IQA) between a reference zone and its warped zone. We show that cosine angle distance-based measures are more efficient than euclidean distance-based for the planar/non-planar classification and that the Universal Quality Image (UQI) measure outperforms the other evaluated measures.
DownloadPaper Citation
in Harvard Style
Bauda M., Chambon S., Gurdjos P. and Charvillat V. (2015). Image Quality Assessment for Photo-consistency Evaluation on Planar Classification in Urban Scenes . In Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-076-5, pages 328-333. DOI: 10.5220/0005222603280333
in Bibtex Style
@conference{icpram15,
author={Marie-Anne Bauda and Sylvie Chambon and Pierre Gurdjos and Vincent Charvillat},
title={Image Quality Assessment for Photo-consistency Evaluation on Planar Classification in Urban Scenes},
booktitle={Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2015},
pages={328-333},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005222603280333},
isbn={978-989-758-076-5},
}
in EndNote Style
TY - CONF
JO - Proceedings of the International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Image Quality Assessment for Photo-consistency Evaluation on Planar Classification in Urban Scenes
SN - 978-989-758-076-5
AU - Bauda M.
AU - Chambon S.
AU - Gurdjos P.
AU - Charvillat V.
PY - 2015
SP - 328
EP - 333
DO - 10.5220/0005222603280333