Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-10859
For citation please use:
Main Title: Remote-Sensing Image Scene Classification With Deep Neural Networks in JPEG 2000 Compressed Domain
Author(s): Preethy Byju, Akshara
Sumbul, Gencer
Demir, Begüm
Bruzzone, Lorenzo
Type: Article
Language Code: en
Abstract: To 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).
URI: https://depositonce.tu-berlin.de/handle/11303/11977
http://dx.doi.org/10.14279/depositonce-10859
Issue Date: 20-Jul-2020
Date Available: 16-Nov-2020
DDC Class: 006 Spezielle Computerverfahren
Subject(s): compressed image domain
deep neural networks
DNNs
joint photographic experts group 2020
JPEG 2020
remote sensing
RS
scene classification
Sponsor/Funder: EC/H2020/759764/EU/Accurate and Scalable Processing of Big Data in Earth Observation/BigEarth
License: http://rightsstatements.org/vocab/InC/1.0/
Journal Title: IEEE Transactions on Geoscience and Remote Sensing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Publisher Place: New York, NY
Publisher DOI: 10.1109/TGRS.2020.3007523
EISSN: 1558-0644
ISSN: 0196-2892
Appears in Collections:FG Remote Sensing Image Analysis Group » Publications

Files in This Item:
preethy-byju_etal_2020.pdf

Accepted manuscript

Format: Adobe PDF | Size: 2.75 MB
DownloadShow Preview
Thumbnail

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.