Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks

Multispectral sensors constitute a core Earth observation image technology generating massive high-dimensional observations. To address the communication and storage constraints of remote sensing platforms, lossy data compression becomes necessary, but it unavoidably introduces unwanted artifacts. I...

Full description

Saved in:
Bibliographic Details
Published in:Journal of imaging 2020-04, Vol.6 (4), p.24
Main Authors: Giannopoulos, Michalis, Aidini, Anastasia, Pentari, Anastasia, Fotiadou, Konstantina, Tsakalides, Panagiotis
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Classification
Cloud cover
compression
convolutional neural networks
Data compression
Datasets
Deep learning
Image classification
Image compression
Image quality
Image retrieval
Land cover
Machine learning
Mathematical analysis
multispectral image classification
Neural networks
Noise
Performance evaluation
quantization
Remote sensing
Remote sensors
residual learning
Satellites
Support vector machines
Tensors
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multispectral sensors constitute a core Earth observation image technology generating massive high-dimensional observations. To address the communication and storage constraints of remote sensing platforms, lossy data compression becomes necessary, but it unavoidably introduces unwanted artifacts. In this work, we consider the encoding of multispectral observations into high-order tensor structures which can naturally capture multi-dimensional dependencies and correlations, and we propose a resource-efficient compression scheme based on quantized low-rank tensor completion. The proposed method is also applicable to the case of missing observations due to environmental conditions, such as cloud cover. To quantify the performance of compression, we consider both typical image quality metrics as well as the impact on state-of-the-art deep learning-based land-cover classification schemes. Experimental analysis on observations from the ESA Sentinel-2 satellite reveals that even minimal compression can have negative effects on classification performance which can be efficiently addressed by our proposed recovery scheme.
ISSN:2313-433X
2313-433X
DOI:10.3390/jimaging6040024