Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F17%3A43932070" target="_blank" >RIV/49777513:23520/17:43932070 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/document/7966418/" target="_blank" >http://ieeexplore.ieee.org/document/7966418/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN.2017.7966418" target="_blank" >10.1109/IJCNN.2017.7966418</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

Popis výsledku v původním jazyce

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[2], second focused on visual geolocalization but relying on accurate detection of skyline [15] nd other two proposed for general semantic segmentation – Fully Convolutional Networks (FCN) [21] and SegNet[22]. Each of the first two methods is trained on a common training set [11] 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.

Název v anglickém jazyce

Comparison of Semantic Segmentation Approaches for Horizon/Sky Line Detection

Popis výsledku anglicky

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[2], second focused on visual geolocalization but relying on accurate detection of skyline [15] nd other two proposed for general semantic segmentation – Fully Convolutional Networks (FCN) [21] and SegNet[22]. Each of the first two methods is trained on a common training set [11] 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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/LO1506" target="_blank" >LO1506: Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnost</a><br>

Návaznosti

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

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Neural Networks (IJCNN), 2017 International Joint Conference on

ISBN

978-1-5090-6182-2

ISSN

2161-4393

e-ISSN

—

Počet stran výsledku

8

Strana od-do

4436-4443

Název nakladatele

IEEE

Místo vydání

New York

Místo konání akce

Anchorage, Alaska, USA

Datum konání akce

14. 5. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426968704091