Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods
Nowadays, with the rise of drone and satellite technology, there is a possibility for its application in sea and coastal surveillance. An advantage of this type of application is the automated recognition of marine objects, among which the most important are vessels. This paper presents the principl...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2021-01-01
|
Series: | Tehnički Vjesnik |
Subjects: | |
Online Access: | https://hrcak.srce.hr/file/379428 |
id |
doaj-6aebb1f0e8c44a37aa3f73265efd05cf |
---|---|
record_format |
Article |
spelling |
doaj-6aebb1f0e8c44a37aa3f73265efd05cf2021-07-22T22:38:09ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek Tehnički Vjesnik1330-36511848-63392021-01-0128412211226Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF MethodsJelena Musulin*0Ivan Lorencin1Hrvoje Meštrić2Zlatan Car3Faculty of Engineering, University of Rijeka, Vukovarska 58, 51000 RijekaFaculty of Engineering, University of Rijeka, Vukovarska 58, 51000 RijekaCatolic University of Croatia, Ilica 242, 10000 ZagrebFaculty of Engineering, University of Rijeka, Vukovarska 58, 51000 RijekaNowadays, with the rise of drone and satellite technology, there is a possibility for its application in sea and coastal surveillance. An advantage of this type of application is the automated recognition of marine objects, among which the most important are vessels. This paper presents the principle of vessel recognition based on the extraction of satellite image features of the vessel and the application of a multilayer perceptron (MLP). Dataset used in this research contains the total of 2750 images, where 2112 images are used as training set while the remaining 638 images are used for testing purposes. The SIFT and SURF algorithms were used to extract image features, which were later used as the input vector for MLP.The best results are achieved if a model with four hidden layers is used. These layers are constructed with 32, 128, 32, 128 neurons with ReLU activation function, respectively. Regarding the application of feature extraction, it can be observed that better results are achieved if the SIFT algorithm is used. The ROC AUC value achieved with the combination of SIFT and MLP reaches 0.99.https://hrcak.srce.hr/file/379428MLPSatellite ImagesSIFTSURFVessels Classification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jelena Musulin* Ivan Lorencin Hrvoje Meštrić Zlatan Car |
spellingShingle |
Jelena Musulin* Ivan Lorencin Hrvoje Meštrić Zlatan Car Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods Tehnički Vjesnik MLP Satellite Images SIFT SURF Vessels Classification |
author_facet |
Jelena Musulin* Ivan Lorencin Hrvoje Meštrić Zlatan Car |
author_sort |
Jelena Musulin* |
title |
Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods |
title_short |
Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods |
title_full |
Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods |
title_fullStr |
Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods |
title_full_unstemmed |
Intelligent Automation System for Vessels Recognition: Comparison of SIFT and SURF Methods |
title_sort |
intelligent automation system for vessels recognition: comparison of sift and surf methods |
publisher |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
series |
Tehnički Vjesnik |
issn |
1330-3651 1848-6339 |
publishDate |
2021-01-01 |
description |
Nowadays, with the rise of drone and satellite technology, there is a possibility for its application in sea and coastal surveillance. An advantage of this type of application is the automated recognition of marine objects, among which the most important are vessels. This paper presents the principle of vessel recognition based on the extraction of satellite image features of the vessel and the application of a multilayer perceptron (MLP). Dataset used in this research contains the total of 2750 images, where 2112 images are used as training set while the remaining 638 images are used for testing purposes. The SIFT and SURF algorithms were used to extract image features, which were later used as the input vector for MLP.The best results are achieved if a model with four hidden layers is used. These layers are constructed with 32, 128, 32, 128 neurons with ReLU activation function, respectively. Regarding the application of feature extraction, it can be observed that better results are achieved if the SIFT algorithm is used. The ROC AUC value achieved with the combination of SIFT and MLP reaches 0.99. |
topic |
MLP Satellite Images SIFT SURF Vessels Classification |
url |
https://hrcak.srce.hr/file/379428 |
work_keys_str_mv |
AT jelenamusulin intelligentautomationsystemforvesselsrecognitioncomparisonofsiftandsurfmethods AT ivanlorencin intelligentautomationsystemforvesselsrecognitioncomparisonofsiftandsurfmethods AT hrvojemestric intelligentautomationsystemforvesselsrecognitioncomparisonofsiftandsurfmethods AT zlatancar intelligentautomationsystemforvesselsrecognitioncomparisonofsiftandsurfmethods |
_version_ |
1721290989808648192 |