Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(Shahzad Muhammad) > Burnt Forest Estima...

Abid, Nosheen,1993-Luleå tekniska universitet,EISLAB,Deep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan; School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan (författare)

Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning

Artikel/kapitelEngelska2021

Förlag, utgivningsår, omfång ...

IEEE,2021
printrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:DiVA.org:ltu-87545
https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-87545URI
https://doi.org/10.1109/DICTA52665.2021.9647174DOI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:ref swepub-contenttype
Ämneskategori:kon swepub-publicationtype

Anmärkningar

ISBN för värdpublikation: 978-1-6654-1709-9 (elektronisk)
Massive wildfires not only in Australia, but also worldwide are burning millions of hectares of forests and green land affecting the social, ecological, and economical situation. Widely used indices-based threshold methods like Normalized Burned Ratio (NBR) require a huge amount of data preprocessing and are specific to the data capturing source. State-of-the-art deep learning models, on the other hand, are supervised and require domain experts knowledge for labeling the data in huge quantity. These limitations make the existing models difficult to be adaptable to new variations in the data and capturing sources. In this work, we have proposed an unsupervised deep learning based architecture to map the burnt regions of forests by learning features progressively. The model considers small patches of satellite imagery and classifies them into burnt and not burnt. These small patches are concatenated into binary masks to segment out the burnt region of the forests. The proposed system is composed of two modules: 1) a state-of-the-art deep learning architecture for feature extraction and 2) a clustering algorithm for the generation of pseudo labels to train the deep learning architecture. The proposed method is capable of learning the features progressively in an unsupervised fashion from the data with pseudo labels, reducing the exhausting efforts of data labeling that requires expert knowledge. We have used the realtime data of Sentinel-2 for training the model and mapping the burnt regions. The obtained F1-Score of 0.87 demonstrates the effectiveness of the proposed model.

Ämnesord och genrebeteckningar

NATURVETENSKAP Data- och informationsvetenskap Datavetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Sciences hsv//eng
Unsupervised
Deep Learning
Australia
Forest Fire
Wildfire
Sentinel-2
Aerial Imagery
Machine Learning
Maskininlärning

Biuppslag (personer, institutioner, konferenser, titlar ...)

Malik, Muhammad ImranDeep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan; School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan (författare)
Shahzad, MuhammadDeep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan; School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan; Technical University of Munich (TUM), Munich, Germany (författare)
Shafait, FaisalDeep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan; School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan (författare)
Ali, HaiderEngineering, TU, Kaiserslautern, Germany (författare)
Ghaffar, Muhammad MohsinJohns Hopkins University, USA (författare)
Weis, ChristianJohns Hopkins University, USA (författare)
Wehn, NorbertJohns Hopkins University, USA (författare)
Liwicki, MarcusLuleå tekniska universitet,EISLAB(Swepub:ltu)marliw (författare)
Luleå tekniska universitetEISLAB (creator_code:org_t)

Sammanhörande titlar

Ingår i:Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA): IEEE, s. 74-81

Internetlänk

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Abid, Nosheen, 1 ...; Malik, Muhammad ...; Shahzad, Muhamma ...; Shafait, Faisal; Ali, Haider; Ghaffar, Muhamma ...; visa fler...; Weis, Christian; Wehn, Norbert; Liwicki, Marcus; visa färre...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datavetenskap

Artiklar i publikationen: Proceedings of t ...

Av lärosätet: Luleå tekniska universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se