A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images
In this paper, a novel data augmentation method was proposed for supervised sea ice scene classification with arctic aerial images. Ice-type classification of sea ice scenes in a region is useful for instant navigation. However, some types of sea ice scenes are difficult to collect. The small number...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8766095/ |
id |
doaj-ccf8540c33fc4f23b51e1ad18a2df222 |
---|---|
record_format |
Article |
spelling |
doaj-ccf8540c33fc4f23b51e1ad18a2df2222021-04-05T17:14:16ZengIEEEIEEE Access2169-35362019-01-01710424110424910.1109/ACCESS.2019.29298618766095A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial ImagesYiming Yan0Chunming Zhang1https://orcid.org/0000-0001-7008-2898Nan Su2https://orcid.org/0000-0001-9601-536XDepartment of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaDepartment of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaDepartment of Information and Communication Engineering, Harbin Engineering University, Harbin, ChinaIn this paper, a novel data augmentation method was proposed for supervised sea ice scene classification with arctic aerial images. Ice-type classification of sea ice scenes in a region is useful for instant navigation. However, some types of sea ice scenes are difficult to collect. The small number of available samples usually limits the performance in classification. Inspiring by the transfer learning method, the training samples are augmented with simulated sea ice images. Considering the distribution characteristic of sea ice scene, simulation samples are synthesized by algebraic operations on the respective regions of interest from two true samples. One of the two true samples can be an additional image, which is more easily collected than others, such as full ice and snow. Simultaneously, it introduces new information. Generalization and error-correction capability of deep neural networks for training samples make the proposed method feasible. The experiments on true sample sets, simulation sample sets, and mixed sample sets were implemented. Finally, the effectiveness of our data augmentation method was demonstrated, which improved the accuracy of sea ice classification.https://ieeexplore.ieee.org/document/8766095/Data augmentationscene classificationsea icetransfer learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yiming Yan Chunming Zhang Nan Su |
spellingShingle |
Yiming Yan Chunming Zhang Nan Su A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images IEEE Access Data augmentation scene classification sea ice transfer learning |
author_facet |
Yiming Yan Chunming Zhang Nan Su |
author_sort |
Yiming Yan |
title |
A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images |
title_short |
A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images |
title_full |
A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images |
title_fullStr |
A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images |
title_full_unstemmed |
A Novel Data Augmentation Method for Sea Ice Scene Classification of Arctic Aerial Images |
title_sort |
novel data augmentation method for sea ice scene classification of arctic aerial images |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
In this paper, a novel data augmentation method was proposed for supervised sea ice scene classification with arctic aerial images. Ice-type classification of sea ice scenes in a region is useful for instant navigation. However, some types of sea ice scenes are difficult to collect. The small number of available samples usually limits the performance in classification. Inspiring by the transfer learning method, the training samples are augmented with simulated sea ice images. Considering the distribution characteristic of sea ice scene, simulation samples are synthesized by algebraic operations on the respective regions of interest from two true samples. One of the two true samples can be an additional image, which is more easily collected than others, such as full ice and snow. Simultaneously, it introduces new information. Generalization and error-correction capability of deep neural networks for training samples make the proposed method feasible. The experiments on true sample sets, simulation sample sets, and mixed sample sets were implemented. Finally, the effectiveness of our data augmentation method was demonstrated, which improved the accuracy of sea ice classification. |
topic |
Data augmentation scene classification sea ice transfer learning |
url |
https://ieeexplore.ieee.org/document/8766095/ |
work_keys_str_mv |
AT yimingyan anoveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages AT chunmingzhang anoveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages AT nansu anoveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages AT yimingyan noveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages AT chunmingzhang noveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages AT nansu noveldataaugmentationmethodforseaicesceneclassificationofarcticaerialimages |
_version_ |
1721540064944586752 |