Resource Efficient Mountainous Skyline Extraction using Shallow Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU140739" target="_blank" >RIV/00216305:26230/21:PU140739 - isvavai.cz</a>

Výsledek na webu

<a href="http://cadik.posvete.cz/papers/IJCNN21_Skyline_Final.pdf" target="_blank" >http://cadik.posvete.cz/papers/IJCNN21_Skyline_Final.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN52387.2021.9533859" target="_blank" >10.1109/IJCNN52387.2021.9533859</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Resource Efficient Mountainous Skyline Extraction using Shallow Learning

Popis výsledku v původním jazyce

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

Název v anglickém jazyce

Resource Efficient Mountainous Skyline Extraction using Shallow Learning

Popis výsledku anglicky

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

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LTAIZ19004" target="_blank" >LTAIZ19004: Topografická analýza obrazu s využitím metod hlubokého učení</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the International Joint Conference on Neural Networks (IJCNN)

ISBN

978-1-6654-3900-8

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

1-9

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

Hoffman Estates

Místo konání akce

USA

Datum konání akce

18. 7. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000722581704065