Publication Details

Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

AHMAD Touqeer, CAMPR Pavel, ČADÍK Martin and BEBIS George. Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN). Anchorage: Institute of Electrical and Electronics Engineers, 2017, pp. 4436-4443. ISBN 978-1-4799-1961-1. Available from: http://cadik.posvete.cz/papers/ahmad17comparison.pdf
Czech title
Porovnání metod sémantické segmentace pro detekci horizontu
Type
conference paper
Language
english
Authors
Ahmad Touqeer (UNR)
Campr Pavel (WBU in Pilsen)
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
Bebis George (UNR)
URL
Keywords

horizon detection, skyline detection, geo-localization, segmentation methods, semantic segmentation, Fully Convolutional Networks

Abstract

Horizon or skyline detection plays a vital role towards mountainous visual geo-localization, however most of the recently proposed visual geo-localization approaches rely on user-in-the-loop skyline detection methods. Detecting such a segmenting boundary fully autonomously would definitely be a step forward for these localization approaches. This paper provides a quantitative comparison of four such methods for autonomous horizon/sky line detection on an extensive data set. Specifically, we provide the comparison between four recently proposed segmentation methods; one explicitly targeting the problem of horizon detection, second focused on visual geo-localization but relying on accurate detection of skyline and other two proposed for general semantic segmentation -- Fully Convolutional Networks (FCN) and SegNet. Each of the first two methods is trained on a common training set comprised of about 200 images while models for the third and fourth method are fine tuned for sky segmentation problem through transfer learning using the same data set. Each of the method is tested on an extensive test set (about 3K images) covering various challenging geographical, weather, illumination and seasonal conditions. We report average accuracy and average absolute pixel error for each of the presented formulation.

Published
2017
Pages
4436-4443
Proceedings
Proceedings of the International Joint Conference on Neural Networks (IJCNN)
Conference
The 2017 International Joint Conference on Neural Networks, William A. Egan Civic and Convention Center in Anchorage, Alaska, USA, US
ISBN
978-1-4799-1961-1
Publisher
Institute of Electrical and Electronics Engineers
Place
Anchorage, US
DOI
UT WoS
000426968704091
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11352,
   author = "Touqeer Ahmad and Pavel Campr and Martin \v{C}ad\'{i}k and George Bebis",
   title = "Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection",
   pages = "4436--4443",
   booktitle = "Proceedings of the International Joint Conference on Neural Networks (IJCNN)",
   year = 2017,
   location = "Anchorage, US",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "978-1-4799-1961-1",
   doi = "10.1109/IJCNN.2017.7966418",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11352"
}
Back to top