SAR automatic target recognition based on convolutional neural networks

Simple item page
dc.contributor.authorKechagias-Stamatis, Odysseas
dc.contributor.authorAouf, Nabil
dc.contributor.authorBelloni, Carole D. L.
dc.date.accessioned2019-05-02T18:52:09Z
dc.date.available2019-05-02T18:52:09Z
dc.date.issued2018-05-28
dc.description.abstractWe propose a multi-modal multi-discipline strategy appropriate for Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) imagery. Our architecture relies on a pre-trained, in the RGB domain, Convolutional Neural Network that is innovatively applied on SAR imagery, and is combined with multiclass Support Vector Machine classification. The multi-modal aspect of our architecture enforces the generalisation capabilities of our proposal, while the multi-discipline aspect bridges the modality gap. Even though our technique is trained in a single depression angle of 17°, average performance on the MSTAR database over a 10-class target classification problem in 15°, 30° and 45° depression is 97.8%. This multi-target and multi-depression ATR capability has not been reported yet in the MSTAR database literature.en_UK
dc.identifier.citationO Kechagias-Stamatis, N Aouf and CDL Belloni. SAR automatic target recognition based on convolutional neural networks. In: IET International Conference on Radar Systems (Radar 2017), Belfast, 23-26 October 2017en_UK
dc.identifier.isbn978-1-78561-673-0
dc.identifier.uri10.1049/cp.2017.0437
dc.identifier.urihttps://ieeexplore.ieee.org/document/8367522
dc.identifier.urihttp://dspace.lib.cranfield.ac.uk/handle/1826/14127
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectAutomatic Target recognitionen_UK
dc.subjectConvolutional Neural Networksen_UK
dc.subjectDeep Learningen_UK
dc.subjectSupport Vector Machineen_UK
dc.subjectSynthetic Aperture Radaren_UK
dc.titleSAR automatic target recognition based on convolutional neural networksen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
SAR_automatic_target_recognition-2017.pdf
Size:
290.19 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (CDS)