Enhancement of Ship Type Classification from a Combination of CNN and KNN
Ship type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships,...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/10/1169 |
id |
doaj-5b6d21db0d224fb0a887da85186517bc |
---|---|
record_format |
Article |
spelling |
doaj-5b6d21db0d224fb0a887da85186517bc2021-05-31T23:58:13ZengMDPI AGElectronics2079-92922021-05-01101169116910.3390/electronics10101169Enhancement of Ship Type Classification from a Combination of CNN and KNNHo-Kun Jeon0Chan-Su Yang1Marine Security and Safety Research Center, Korea Institute of Ocean Science & Technology, Busan 49111, KoreaMarine Security and Safety Research Center, Korea Institute of Ocean Science & Technology, Busan 49111, KoreaShip type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships, such as length and breadth, can be easily obtained from various sources and can be utilized in a classification with k-nearest neighbor (KNN). This study proposes a method to improve the efficiency of ship type classification from Sentinel-1 dual-polarization data with 10 m pixel spacing using both CNN and KNN models. In the first stage, Sentinel-1 intensity images centered on ship positions were used in a rectangular shape to apply an image processing procedure such as head-up, padding and image augmentation. The process increased the accuracy by 33.0% and 31.7% for VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization compared to the CNN-based classification with original ship images, respectively. In the second step, a combined method of CNN and KNN was compared with a CNN-alone case. The f1-score of CNN alone was up to 85.0%, whereas the combination method showed up to 94.3%, which was a 9.3% increase. In the future, more details on an optimization method will be investigated through field experiments of ship classification.https://www.mdpi.com/2079-9292/10/10/1169ship classificationCNNKNNSentinel-1 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ho-Kun Jeon Chan-Su Yang |
spellingShingle |
Ho-Kun Jeon Chan-Su Yang Enhancement of Ship Type Classification from a Combination of CNN and KNN Electronics ship classification CNN KNN Sentinel-1 |
author_facet |
Ho-Kun Jeon Chan-Su Yang |
author_sort |
Ho-Kun Jeon |
title |
Enhancement of Ship Type Classification from a Combination of CNN and KNN |
title_short |
Enhancement of Ship Type Classification from a Combination of CNN and KNN |
title_full |
Enhancement of Ship Type Classification from a Combination of CNN and KNN |
title_fullStr |
Enhancement of Ship Type Classification from a Combination of CNN and KNN |
title_full_unstemmed |
Enhancement of Ship Type Classification from a Combination of CNN and KNN |
title_sort |
enhancement of ship type classification from a combination of cnn and knn |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2021-05-01 |
description |
Ship type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships, such as length and breadth, can be easily obtained from various sources and can be utilized in a classification with k-nearest neighbor (KNN). This study proposes a method to improve the efficiency of ship type classification from Sentinel-1 dual-polarization data with 10 m pixel spacing using both CNN and KNN models. In the first stage, Sentinel-1 intensity images centered on ship positions were used in a rectangular shape to apply an image processing procedure such as head-up, padding and image augmentation. The process increased the accuracy by 33.0% and 31.7% for VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization compared to the CNN-based classification with original ship images, respectively. In the second step, a combined method of CNN and KNN was compared with a CNN-alone case. The f1-score of CNN alone was up to 85.0%, whereas the combination method showed up to 94.3%, which was a 9.3% increase. In the future, more details on an optimization method will be investigated through field experiments of ship classification. |
topic |
ship classification CNN KNN Sentinel-1 |
url |
https://www.mdpi.com/2079-9292/10/10/1169 |
work_keys_str_mv |
AT hokunjeon enhancementofshiptypeclassificationfromacombinationofcnnandknn AT chansuyang enhancementofshiptypeclassificationfromacombinationofcnnandknn |
_version_ |
1721416110514896896 |