Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data
Hyperspectral remote sensing technology can acquire nearly continuous spectrum information and rich sea ice image information, thus providing an important means of sea ice detection. However, the correlation and redundancy among hyperspectral bands reduce the accuracy of traditional sea ice detectio...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/17/5/1124 |
id |
doaj-6bde7adbac534dc9be86445c98a62e12 |
---|---|
record_format |
Article |
spelling |
doaj-6bde7adbac534dc9be86445c98a62e122020-11-24T20:41:59ZengMDPI AGSensors1424-82202017-05-01175112410.3390/s17051124s17051124Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral DataYanling Han0Jue Li1Yun Zhang2Zhonghua Hong3Jing Wang4College of Information Technology, Shanghai Ocean University; Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University; Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University; Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University; Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University; Shanghai 201306, ChinaHyperspectral remote sensing technology can acquire nearly continuous spectrum information and rich sea ice image information, thus providing an important means of sea ice detection. However, the correlation and redundancy among hyperspectral bands reduce the accuracy of traditional sea ice detection methods. Based on the spectral characteristics of sea ice, this study presents an improved similarity measurement method based on linear prediction (ISMLP) to detect sea ice. First, the first original band with a large amount of information is determined based on mutual information theory. Subsequently, a second original band with the least similarity is chosen by the spectral correlation measuring method. Finally, subsequent bands are selected through the linear prediction method, and a support vector machine classifier model is applied to classify sea ice. In experiments performed on images of Baffin Bay and Bohai Bay, comparative analyses were conducted to compare the proposed method and traditional sea ice detection methods. Our proposed ISMLP method achieved the highest classification accuracies (91.18% and 94.22%) in both experiments. From these results the ISMLP method exhibits better performance overall than other methods and can be effectively applied to hyperspectral sea ice detection.http://www.mdpi.com/1424-8220/17/5/1124sea icesimilarity measureband selectionclassificationhyperspectral image |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yanling Han Jue Li Yun Zhang Zhonghua Hong Jing Wang |
spellingShingle |
Yanling Han Jue Li Yun Zhang Zhonghua Hong Jing Wang Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data Sensors sea ice similarity measure band selection classification hyperspectral image |
author_facet |
Yanling Han Jue Li Yun Zhang Zhonghua Hong Jing Wang |
author_sort |
Yanling Han |
title |
Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data |
title_short |
Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data |
title_full |
Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data |
title_fullStr |
Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data |
title_full_unstemmed |
Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data |
title_sort |
sea ice detection based on an improved similarity measurement method using hyperspectral data |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2017-05-01 |
description |
Hyperspectral remote sensing technology can acquire nearly continuous spectrum information and rich sea ice image information, thus providing an important means of sea ice detection. However, the correlation and redundancy among hyperspectral bands reduce the accuracy of traditional sea ice detection methods. Based on the spectral characteristics of sea ice, this study presents an improved similarity measurement method based on linear prediction (ISMLP) to detect sea ice. First, the first original band with a large amount of information is determined based on mutual information theory. Subsequently, a second original band with the least similarity is chosen by the spectral correlation measuring method. Finally, subsequent bands are selected through the linear prediction method, and a support vector machine classifier model is applied to classify sea ice. In experiments performed on images of Baffin Bay and Bohai Bay, comparative analyses were conducted to compare the proposed method and traditional sea ice detection methods. Our proposed ISMLP method achieved the highest classification accuracies (91.18% and 94.22%) in both experiments. From these results the ISMLP method exhibits better performance overall than other methods and can be effectively applied to hyperspectral sea ice detection. |
topic |
sea ice similarity measure band selection classification hyperspectral image |
url |
http://www.mdpi.com/1424-8220/17/5/1124 |
work_keys_str_mv |
AT yanlinghan seaicedetectionbasedonanimprovedsimilaritymeasurementmethodusinghyperspectraldata AT jueli seaicedetectionbasedonanimprovedsimilaritymeasurementmethodusinghyperspectraldata AT yunzhang seaicedetectionbasedonanimprovedsimilaritymeasurementmethodusinghyperspectraldata AT zhonghuahong seaicedetectionbasedonanimprovedsimilaritymeasurementmethodusinghyperspectraldata AT jingwang seaicedetectionbasedonanimprovedsimilaritymeasurementmethodusinghyperspectraldata |
_version_ |
1716823675215282176 |