Publication:
Scene classification for aerial images based on CNN using sparse coding technique

Simple item page
dc.citedby39
dc.contributor.authorQayyum A.en_US
dc.contributor.authorMalik A.S.en_US
dc.contributor.authorSaad N.M.en_US
dc.contributor.authorIqbal M.en_US
dc.contributor.authorFaris Abdullah M.en_US
dc.contributor.authorRasheed W.en_US
dc.contributor.authorRashid Abdullah T.A.en_US
dc.contributor.authorBin Jafaar M.Y.en_US
dc.contributor.authorid57211138712en_US
dc.contributor.authorid12800348400en_US
dc.contributor.authorid56567441400en_US
dc.contributor.authorid54386959400en_US
dc.contributor.authorid57188825497en_US
dc.contributor.authorid24475459400en_US
dc.contributor.authorid56594684600en_US
dc.contributor.authorid57193519737en_US
dc.date.accessioned2023-05-29T06:38:35Z
dc.date.available2023-05-29T06:38:35Z
dc.date.issued2017
dc.descriptionAntennas; Classification (of information); Codes (symbols); Convolution; Image classification; Neural networks; Remote sensing; Satellite imagery; Semantics; Unmanned aerial vehicles (UAV); Convolutional Neural Networks (CNN); Future applications; High resolution remote sensing imagery; Mid-level features; Multi-scale features; Robust performance; Scale invariant feature transforms; Scene classification; Image coding; aircraft; artificial neural network; image classification; satellite imagery; unmanned vehicleen_US
dc.description.abstractAerial scene classification purposes to automatically label aerial images with specific semantic categories. However, cataloguing presents a fundamental problem for high-resolution remote-sensing imagery (HRRS). Recent developments include several approaches and numerous algorithms address the task. This article proposes a convolutional neural network (CNN) approach that utilizes sparse coding for scene classification applicable for HRRS unmanned aerial vehicle (UAV) and satellite imagery. The article has two major sections: the first describes the extraction of dense multiscale features (multiple scales) from the last convolutional layer of a pre-trained CNN models; the second describes the encoding of extracted features into global image features via sparse coding to achieve scene classification. The authors compared experimental outcomes with existing techniques such as Scale-Invariant Feature Transform and demonstrated that features from pre-trained CNNs generalized well with HRRS datasets and were more expressive than low- and mid-level features, exhibiting an overall 90.3% accuracy rate for scene classification compared to 85.4% achieved by SIFT with sparse coding. Thus, the proposed CNN-based sparse coding approach obtained a robust performance that holds promising potential for future applications in satellite and UAV imaging. � 2017 Informa UK Limited, trading as Taylor & Francis Group.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1080/01431161.2017.1296206
dc.identifier.epage2685
dc.identifier.issue8-Oct
dc.identifier.scopus2-s2.0-85014553885
dc.identifier.spage2662
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85014553885&doi=10.1080%2f01431161.2017.1296206&partnerID=40&md5=c41a65077a8f7c4fbc7f59ab0a7955ef
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/23227
dc.identifier.volume38
dc.publisherTaylor and Francis Ltd.en_US
dc.sourceScopus
dc.sourcetitleInternational Journal of Remote Sensing
dc.titleScene classification for aerial images based on CNN using sparse coding techniqueen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS