UCL: Unsupervised Curriculum Learning for Water Body Classification from Remote Sensing Imagery

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

Validerad;2021;Nivå 2;2021-11-08 (johcin);Full text license: CC BY-NC-ND
This paper presents a Convolutional Neural Networks (CNN) based Unsupervised Curriculum Learning approach for the recognition of water bodies to overcome the stated challenges for remote sensing based RGB imagery. The unsupervised nature of the presented algorithm eliminates the need for labelled training data. The problem is cast as a two class clustering problem (water and non-water), while clustering is done on deep features obtained by a pre-trained CNN. After initial clusters have been identified, representative samples from each cluster are chosen by the unsupervised curriculum learning algorithm for fine-tuning the feature extractor. The stated process is repeated iteratively until convergence. Three datasets have been used to evaluate the approach and show its effectiveness on varying scales: (i) SAT-6 dataset comprising high resolution aircraft images, (ii) Sentinel-2 of EuroSAT, comprising remote sensing images with low resolution, and (iii) PakSAT, a new dataset we created for this study. PakSAT is the first Pakistani Sentinel-2 dataset designed to classify water bodies of Pakistan. Extensive experiments on these datasets demonstrate the progressive learning behaviour of UCL and reported promising results of water classification on all three datasets. The obtained accuracies outperform the supervised methods in domain adaptation, demonstrating the effectiveness of the proposed algorithm.

Shahzad, MuhammadSchool of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan; Deep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan; Data Science in Earth Observation, Department of Aerospace and Geodesy, Technical University of Munich (TUM), Munich, Germany (författare)
Malik, Muhammad ImranSchool of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan; Deep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan (författare)
Schwanecke, UlrichRheinMain University of Applied Sciences, Germany (författare)
Ulges, AdrianRheinMain University of Applied Sciences, Germany (författare)
Kovács, György,Postdoctoral researcher,1984-Luleå tekniska universitet,EISLAB(Swepub:ltu)gyokov (författare)
Shafait, FaisalSchool of Electrical Engineering and Computer Science, National University of Sciences and Technology, Pakistan; Deep Learning Lab, National Center of Artificial Intelligence, National University of Sciences and Technology, Pakistan (författare)
Luleå tekniska universitetEISLAB (creator_code:org_t)

Ingår i:International Journal of Applied Earth Observation and Geoinformation: Elsevier1051569-84321872-826X

Av författaren/redakt...: Abid, Nosheen, 1 ...; Shahzad, Muhamma ...; Malik, Muhammad ...; Schwanecke, Ulri ...; Ulges, Adrian; Kovács, György, ...; visa fler...; Shafait, Faisal; visa färre...

Om ämnet

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.