Synthetic Aperture Radar (SAR) constitutes a fundamental asset for wide-areas monitoring with high-resolution requirements. The first SAR sensors have given rise to coarse coastal and maritime monitoring applications, including oil spill, ship and ice floes detection. With the upgrade to very high-resolution sensors in the recent years, with relatively new SAR missions such as Sentinel-1, a great deal of data providing a stronger information content has been released, enabling more refined studies on general targets features and thus permitting complex classifications, as for ship classification, which has become increasingly relevant given the growing need for coastal surveillance in commercial and military segments. In the last decade, several works focused on this topic have been presented, generally based on radiometric features processing; furthermore, in the very recent years a significant amount of research works have focused on emerging deep learning techniques, in particular on Convolutional Neural Networks (CNN). Recently Capsule Neural Networks (CapsNets) have been presented, demonstrating a notable improvement in capturing the properties of given entities, improving the use of spatial informations, in particular of spatial dependence between features, a severely lacking feature in CNNs. In fact, CNNs pooling operations have been criticized for losing spatial relations, thus special capsules, along with a new iterative routing-by-agreement mechanism, have been proposed. In this work a comparison between Capsule and CNNs potential in the ship classification application domain is shown, by leveraging the OpenSARShip, a SAR Sentinel-1 ship chips dataset; in particular, a performance comparison between capsule and various convolutional architectures is built, demonstrating better performances of CapsNet in classifying ships within a small dataset.

De Laurentiis, L., Pomente, A., Del Frate, F., Schiavon, G. (2019). Capsule and convolutional neural network-based SAR ship classification in Sentinel-1 data. In Proceedings of SPIE - The International Society for Optical Engineering (pp.4). 1000 20TH ST, PO BOX 10, BELLINGHAM, WA 98227-0010 USA : SPIE [10.1117/12.2532551].

Capsule and convolutional neural network-based SAR ship classification in Sentinel-1 data

De Laurentiis L.;Del Frate F.;Schiavon G.
2019-01-01

Abstract

Synthetic Aperture Radar (SAR) constitutes a fundamental asset for wide-areas monitoring with high-resolution requirements. The first SAR sensors have given rise to coarse coastal and maritime monitoring applications, including oil spill, ship and ice floes detection. With the upgrade to very high-resolution sensors in the recent years, with relatively new SAR missions such as Sentinel-1, a great deal of data providing a stronger information content has been released, enabling more refined studies on general targets features and thus permitting complex classifications, as for ship classification, which has become increasingly relevant given the growing need for coastal surveillance in commercial and military segments. In the last decade, several works focused on this topic have been presented, generally based on radiometric features processing; furthermore, in the very recent years a significant amount of research works have focused on emerging deep learning techniques, in particular on Convolutional Neural Networks (CNN). Recently Capsule Neural Networks (CapsNets) have been presented, demonstrating a notable improvement in capturing the properties of given entities, improving the use of spatial informations, in particular of spatial dependence between features, a severely lacking feature in CNNs. In fact, CNNs pooling operations have been criticized for losing spatial relations, thus special capsules, along with a new iterative routing-by-agreement mechanism, have been proposed. In this work a comparison between Capsule and CNNs potential in the ship classification application domain is shown, by leveraging the OpenSARShip, a SAR Sentinel-1 ship chips dataset; in particular, a performance comparison between capsule and various convolutional architectures is built, demonstrating better performances of CapsNet in classifying ships within a small dataset.
Active and Passive Microwave Remote Sensing for Environmental Monitoring III 2019
fra
2019
The Society of Photo-Optical Instrumentation Engineers (SPIE)
Rilevanza internazionale
contributo
2019
Settore ING-INF/02 - CAMPI ELETTROMAGNETICI
English
Capsule; Classication; Convolutional; Deep Learning; Detection; Generative Adversarial; Neural Networks; SAR; Sentinel; Ship
Intervento a convegno
De Laurentiis, L., Pomente, A., Del Frate, F., Schiavon, G. (2019). Capsule and convolutional neural network-based SAR ship classification in Sentinel-1 data. In Proceedings of SPIE - The International Society for Optical Engineering (pp.4). 1000 20TH ST, PO BOX 10, BELLINGHAM, WA 98227-0010 USA : SPIE [10.1117/12.2532551].
De Laurentiis, L; Pomente, A; Del Frate, F; Schiavon, G
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/242294
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 9
social impact