Please use this identifier to cite or link to this item:
Title: Performance evaluation of state-of-The-Art CNN architectures for the on-board processing of remotely sensed images
Authors: Neris Tomé, Romén 
Guerra, Rael
Lopez, Sebastian 
Sarmiento, Roberto 
UNESCO Clasification: 3307 Tecnología electrónica
Keywords: Deep Learning
Machine Learning
Neural Networks
Remote Sensing
Target Detection
Issue Date: 2021
Journal: Proceedings (Conference on Design of Circuits and Integrated Systems) 
Conference: 36th Conference on Design of Circuits and Integrated Systems - DCIS 2021
Abstract: Over the last few years, Convolutional Neural Networks (CNNs) have been extensively used in different remote sensing applications. However, for large networks the computation and memory requirements have brought many challenges into this field. Additionally, the computational capabilities of hardware devices available on-board satellites is limited, being this another constraint for these implementations. In this paper, the authors present the evaluation of nine different CNN architectures for ship and airplane detection, taking into consideration that the final use-case application will be an on-board system with target detection capabilities.
ISBN: 9781665421164
DOI: 10.1109/DCIS53048.2021.9666179
Source: 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021 [EISSN 2640-5563], (Enero 2021)
Appears in Collections:Actas de congresos
Show full item record


checked on Mar 26, 2023

Page view(s)

checked on Feb 25, 2023

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.