2018
Thapa, Laxmi
Ship recognition on the sea surface using aerial images taken by UAV: a deep learning approach Masters Thesis
Universidade Nova de Lisboa. Information management school, Lisbon, 2018.
Abstract | Links | BibTeX | Tags: Mastergeotech, unmanned air systems
@mastersthesis{Thapa2018b,
title = {Ship recognition on the sea surface using aerial images taken by UAV: a deep learning approach},
author = {Laxmi Thapa},
editor = {V.J. Lobo and Mauro Castelli and Joaquín Torres-Sospedra (supervisors) },
url = {http://hdl.handle.net/10362/63805},
year = {2018},
date = {2018-02-28},
address = {Lisbon},
school = {Universidade Nova de Lisboa. Information management school},
abstract = {Oceans are very important for mankind, because they are a very important source of food, they have a very large impact on the global environmental equilibrium, and it is over the oceans that most of the world commerce is done. Thus, maritime surveillance and monitoring, in particular identifying the ships used, is of great importance to oversee activities like fishing, marine transportation, navigation in general, illegal border encroachment, and search and rescue operations. In this thesis, we used images obtained with Unmanned Aerial Vehicles (UAVs) over the Atlantic Ocean to identify what type of ship (if any) is present in a given location. Images generated from UAV cameras suffer from camera motion, scale variability, variability in the sea surface and sun glares. Extracting information from these images is challenging and is mostly done by human operators, but advances in computer vision technology and development of deep learning techniques in recent years have made it possible to do so automatically. We used four of the state-of-art pretrained deep learning network models, namely VGG16, Xception, ResNet and InceptionResNet trained on ImageNet dataset, modified their original structure using transfer learning based fine tuning techniques and then trained them on our dataset to create new models. We managed to achieve very high accuracy (99.6 to 99.9% correct classifications) when classifying the ships that appear on the images of our dataset. With such a high success rate (albeit at the cost of high computing power), we can proceed to implement these algorithms on maritime patrol UAVs, and thus improve Maritime Situational Awareness.},
keywords = {Mastergeotech, unmanned air systems},
pubstate = {published},
tppubtype = {mastersthesis}
}
Oceans are very important for mankind, because they are a very important source of food, they have a very large impact on the global environmental equilibrium, and it is over the oceans that most of the world commerce is done. Thus, maritime surveillance and monitoring, in particular identifying the ships used, is of great importance to oversee activities like fishing, marine transportation, navigation in general, illegal border encroachment, and search and rescue operations. In this thesis, we used images obtained with Unmanned Aerial Vehicles (UAVs) over the Atlantic Ocean to identify what type of ship (if any) is present in a given location. Images generated from UAV cameras suffer from camera motion, scale variability, variability in the sea surface and sun glares. Extracting information from these images is challenging and is mostly done by human operators, but advances in computer vision technology and development of deep learning techniques in recent years have made it possible to do so automatically. We used four of the state-of-art pretrained deep learning network models, namely VGG16, Xception, ResNet and InceptionResNet trained on ImageNet dataset, modified their original structure using transfer learning based fine tuning techniques and then trained them on our dataset to create new models. We managed to achieve very high accuracy (99.6 to 99.9% correct classifications) when classifying the ships that appear on the images of our dataset. With such a high success rate (albeit at the cost of high computing power), we can proceed to implement these algorithms on maritime patrol UAVs, and thus improve Maritime Situational Awareness.
2016
Jordán, Emilio Troncho
A prospective geoinformatic approach to indoor navigation for Unmanned Air System (UAS) by use of quick response (QR) codes Masters Thesis
2016.
BibTeX | Tags: Indoor localization, Indoor positioning, Mastergeotech, unmanned air systems
@mastersthesis{Jordán2016,
title = {A prospective geoinformatic approach to indoor navigation for Unmanned Air System (UAS) by use of quick response (QR) codes },
author = {Emilio Troncho Jordán},
editor = {Ignacio Guerrero (supervisor) and Torsten Prinz (co-supervisor) and Roberto Henriques (co-supervisor)},
year = {2016},
date = {2016-02-26},
keywords = {Indoor localization, Indoor positioning, Mastergeotech, unmanned air systems},
pubstate = {published},
tppubtype = {mastersthesis}
}