Remote-Sensing Image Scene Classification With Deep Neural Networks in JPEG 2000 Compressed Domain

dc.contributor.authorPreethy Byju, Akshara
dc.contributor.authorSumbul, Gencer
dc.contributor.authorDemir, Begüm
dc.contributor.authorBruzzone, Lorenzo
dc.date.accessioned2020-11-16T18:45:16Z
dc.date.available2020-11-16T18:45:16Z
dc.date.issued2020-07-20
dc.description.abstractTo reduce the storage requirements, remote-sensing (RS) images are usually stored in compressed format. Existing scene classification approaches using deep neural networks (DNNs) require to fully decompress the images, which is a computationally demanding task in operational applications. To address this issue, in this article, we propose a novel approach to achieve scene classification in Joint Photographic Experts Group (JPEG) 2000 compressed RS images. The proposed approach consists of two main steps: 1) approximation of the finer resolution subbands of reversible biorthogonal wavelet filters used in JPEG 2000 and 2) characterization of the high-level semantic content of approximated wavelet subbands and scene classification based on the learned descriptors. This is achieved by taking codestreams associated with the coarsest resolution wavelet subband as input to approximate finer resolution subbands using a number of transposed convolutional layers. Then, a series of convolutional layers models the high-level semantic content of the approximated wavelet subband. Thus, the proposed approach models the multiresolution paradigm given in the JPEG 2000 compression algorithm in an end-to-end trainable unified neural network. In the classification stage, the proposed approach takes only the coarsest resolution wavelet subbands as input, thereby reducing the time required to apply decoding. Experimental results performed on two benchmark aerial image archives demonstrate that the proposed approach significantly reduces the computational time with similar classification accuracies when compared with traditional RS scene classification approaches (which requires full image decompression).en
dc.description.sponsorshipEC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation/BigEarthen
dc.identifier.eissn1558-0644
dc.identifier.issn0196-2892
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/11977
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-10859
dc.language.isoenen
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc006 Spezielle Computerverfahrende
dc.subject.othercompressed image domainen
dc.subject.otherdeep neural networksen
dc.subject.otherDNNsen
dc.subject.otherjoint photographic experts group 2020en
dc.subject.otherJPEG 2020en
dc.subject.otherremote sensingen
dc.subject.otherRSen
dc.subject.otherscene classificationen
dc.titleRemote-Sensing Image Scene Classification With Deep Neural Networks in JPEG 2000 Compressed Domainen
dc.typeArticleen
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.doi10.1109/TGRS.2020.3007523en
dcterms.bibliographicCitation.journaltitleIEEE Transactions on Geoscience and Remote Sensingen
dcterms.bibliographicCitation.originalpublishernameInstitute of Electrical and Electronics Engineers (IEEE)en
dcterms.bibliographicCitation.originalpublisherplaceNew York, NYen
tub.accessrights.dnbfreeen
tub.affiliationFak. 4 Elektrotechnik und Informatik>Inst. Technische Informatik und Mikroelektronik>FG Remote Sensing Image Analysis Groupde
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Remote Sensing Image Analysis Groupde
tub.affiliation.instituteInst. Technische Informatik und Mikroelektronikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
Files
Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
preethy-byju_etal_2020.pdf
Size:
2.69 MB
Format:
Adobe Portable Document Format
Description:
Accepted manuscript
Collections