Publication Details

Resource Efficient Mountainous Skyline Extraction using Shallow Learning

AHMAD, T.; EMAMI, E.; ČADÍK, M.; BEBIS, G. Resource Efficient Mountainous Skyline Extraction using Shallow Learning. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). Hoffman Estates: Institute of Electrical and Electronics Engineers, 2021. p. 1-9. ISBN: 978-1-6654-3900-8.
Czech title
Efektivní metoda pro detekci křivky horizontu s využitím mělkého učení
Type
conference paper
Language
English
Authors
URL
Keywords

Skyline Extraction, Skyline Detection, Horizon Line, Horizon Curve, Shallow Learning

Abstract

Skyline plays a  pivotal role in mountainous visual geo-localization and localization/navigation of planetary rovers/UAVs and virtual/augmented reality applications. We present a  novel mountainous skyline detection approach where we adapt a shallow learning approach to learn a set of filters to discriminate between edges belonging to sky-mountain boundary and others coming from different regions. Unlike earlier approaches, which either rely on extraction of explicit feature descriptors and their classification, or fine-tuning general scene parsing deep networks for sky segmentation, our approach learns linear filters based on local structure analysis. At test time, for every candidate edge pixel, a single filter is chosen from the set of learned filters based on pixels structure tensor, and then applied to the patch around it. We then employ dynamic programming to solve the shortest path problem for the resultant multistage graph to get the sky-mountain boundary. The proposed approach is computationally faster than earlier methods while providing comparable performance and is more suitable for resource constrained platforms e.g., mobile devices, planetary rovers and UAVs. We compare our proposed approach against earlier skyline detection methods using four different data sets. Our code is available at https://github.com/TouqeerAhmad/skylinedetection

Published
2021
Pages
1–9
Proceedings
Proceedings of the International Joint Conference on Neural Networks (IJCNN)
ISBN
978-1-6654-3900-8
Publisher
Institute of Electrical and Electronics Engineers
Place
Hoffman Estates
DOI
UT WoS
000722581704065
EID Scopus
BibTeX
@inproceedings{BUT171385,
  author="AHMAD, T. and EMAMI, E. and ČADÍK, M. and BEBIS, G.",
  title="Resource Efficient Mountainous Skyline Extraction using Shallow Learning",
  booktitle="Proceedings of the International Joint Conference on Neural Networks (IJCNN)",
  year="2021",
  pages="1--9",
  publisher="Institute of Electrical and Electronics Engineers",
  address="Hoffman Estates",
  doi="10.1109/IJCNN52387.2021.9533859",
  isbn="978-1-6654-3900-8",
  url="http://cadik.posvete.cz/papers/IJCNN21_Skyline_Final.pdf"
}
Back to top