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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/6/4/24 |
| _version_ | 1797570235737309184 |
|---|---|
| author | Michalis Giannopoulos Anastasia Aidini Anastasia Pentari Konstantina Fotiadou Panagiotis Tsakalides |
| author_facet | Michalis Giannopoulos Anastasia Aidini Anastasia Pentari Konstantina Fotiadou Panagiotis Tsakalides |
| author_sort | Michalis Giannopoulos |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T20:23:01Z |
| format | Article |
| id | doaj.art-39f265f3fb894457817ab66a7161f3e9 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T20:23:01Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-39f265f3fb894457817ab66a7161f3e92023-11-19T22:01:45ZengMDPI AGJournal of Imaging2313-433X2020-04-01642410.3390/jimaging6040024Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural NetworksMichalis Giannopoulos0Anastasia Aidini1Anastasia Pentari2Konstantina Fotiadou3Panagiotis Tsakalides4Signal Processing Lab (SPL), Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Crete, GreeceSignal Processing Lab (SPL), Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Crete, GreeceSignal Processing Lab (SPL), Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Crete, GreeceSignal Processing Lab (SPL), Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Crete, GreeceSignal Processing Lab (SPL), Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Crete, GreeceMultispectral 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.https://www.mdpi.com/2313-433X/6/4/24multispectral image classificationdeep learningconvolutional neural networksresidual learningcompressionquantization |
| spellingShingle | Michalis Giannopoulos Anastasia Aidini Anastasia Pentari Konstantina Fotiadou Panagiotis Tsakalides Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks Journal of Imaging multispectral image classification deep learning convolutional neural networks residual learning compression quantization |
| title | Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks |
| title_full | Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks |
| title_fullStr | Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks |
| title_full_unstemmed | Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks |
| title_short | Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks |
| title_sort | classification of compressed remote sensing multispectral images via convolutional neural networks |
| topic | multispectral image classification deep learning convolutional neural networks residual learning compression quantization |
| url | https://www.mdpi.com/2313-433X/6/4/24 |
| work_keys_str_mv | AT michalisgiannopoulos classificationofcompressedremotesensingmultispectralimagesviaconvolutionalneuralnetworks AT anastasiaaidini classificationofcompressedremotesensingmultispectralimagesviaconvolutionalneuralnetworks AT anastasiapentari classificationofcompressedremotesensingmultispectralimagesviaconvolutionalneuralnetworks AT konstantinafotiadou classificationofcompressedremotesensingmultispectralimagesviaconvolutionalneuralnetworks AT panagiotistsakalides classificationofcompressedremotesensingmultispectralimagesviaconvolutionalneuralnetworks |