Multi-Scale Convolutional SVM Networks for Multi-Class Classification Problems of Remote Sensing Images

Cavallaro, Gabriele; Bazi, Yakoub; Melgani, Farid; Riedel, Morris

doi:10.1109/IGARSS.2019.8899831

Contribution to a conference proceedings/Contribution to a book

FZJ-2019-06502

Multi-Scale Convolutional SVM Networks for Multi-Class Classification Problems of Remote Sensing Images

Cavallaro, G. (Corresponding author)FZJ* ; Bazi, Y. ; Melgani, F. ; Riedel, M.FZJ*

2019
IEEE

[Proceedings] - IEEE, 2019. - ISBN 978-1-5386-9154-0
IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 28 Jul 2019 - 2 Aug 2019 IEEE 875-878 (2019) [10.1109/IGARSS.2019.8899831]

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/23600 doi:10.1109/IGARSS.2019.8899831

Abstract: The classification of land-cover classes in remote sensing images can suit a variety of interdisciplinary applications suchas the interpretation of natural and man-made processes onthe Earth surface. The Convolutional Support Vector Machine (CSVM) network was recently proposed as binary classifier for the detection of objects in Unmanned Aerial Vehicle (UAV) images. The training phase of the CSVM isbased on convolutional layers that learn the kernel weightsvia a set of linear Support Vector Machines (SVMs). Thispaper proposes the Multi-scale Convolutional Support VectorMachine (MCSVM) network, that is an ensemble of CSVMclassifiers which process patches of different spatial sizes andcan deal with multi-class classification problems. The experiments are carried out on the EuroSAT Sentinel-2 dataset andthe results are compared to the one obtained with recent transfer learning approaches based on pre-trained ConvolutionalNeural Networks (CNNs).

Contributing Institute(s):