Underwater Hyperspectral Target Detection with Band Selection
Compared to multi-spectral imagery, hyperspectral imagery has very high spectral resolution with abundant spectral information. In underwater target detection, hyperspectral technology can be advantageous in the sense of a poor underwater imaging environment, complex background, or protective mechan...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/7/1056 |
id |
doaj-b67053436f9c495ea6f57268e005a73b |
---|---|
record_format |
Article |
spelling |
doaj-b67053436f9c495ea6f57268e005a73b2020-11-25T02:04:40ZengMDPI AGRemote Sensing2072-42922020-03-01127105610.3390/rs12071056rs12071056Underwater Hyperspectral Target Detection with Band SelectionXianping Fu0Xiaodi Shang1Xudong Sun2Haoyang Yu3Meiping Song4Chein-I Chang5Information and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation and Technology College, Dalian Maritime University, Dalian 116026, ChinaCompared to multi-spectral imagery, hyperspectral imagery has very high spectral resolution with abundant spectral information. In underwater target detection, hyperspectral technology can be advantageous in the sense of a poor underwater imaging environment, complex background, or protective mechanism of aquatic organisms. Due to high data redundancy, slow imaging speed, and long processing of hyperspectral imagery, a direct use of hyperspectral images in detecting targets cannot meet the needs of rapid detection of underwater targets. To resolve this issue, a fast, hyperspectral underwater target detection approach using band selection (BS) is proposed. It first develops a constrained-target optimal index factor (OIF) band selection (CTOIFBS) to select a band subset with spectral wavelengths specifically responding to the targets of interest. Then, an underwater spectral imaging system integrated with the best-selected band subset is constructed for underwater target image acquisition. Finally, a constrained energy minimization (CEM) target detection algorithm is used to detect the desired underwater targets. Experimental results demonstrate that the band subset selected by CTOIFBS is more effective in detecting underwater targets compared to the other three existing BS methods, uniform band selection (UBS), minimum variance band priority (MinV-BP), and minimum variance band priority with OIF (MinV-BP-OIF). In addition, the results also show that the acquisition and detection speed of the designed underwater spectral acquisition system using CTOIFBS can be significantly improved over the original underwater hyperspectral image system without BS.https://www.mdpi.com/2072-4292/12/7/1056constrained-target optimal index factor band selection (ctoifbs)hyperspectral imageunderwater spectral imaging systemunderwater hyperspectral target detectionband selection (bs)constrained energy minimization (cem) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xianping Fu Xiaodi Shang Xudong Sun Haoyang Yu Meiping Song Chein-I Chang |
spellingShingle |
Xianping Fu Xiaodi Shang Xudong Sun Haoyang Yu Meiping Song Chein-I Chang Underwater Hyperspectral Target Detection with Band Selection Remote Sensing constrained-target optimal index factor band selection (ctoifbs) hyperspectral image underwater spectral imaging system underwater hyperspectral target detection band selection (bs) constrained energy minimization (cem) |
author_facet |
Xianping Fu Xiaodi Shang Xudong Sun Haoyang Yu Meiping Song Chein-I Chang |
author_sort |
Xianping Fu |
title |
Underwater Hyperspectral Target Detection with Band Selection |
title_short |
Underwater Hyperspectral Target Detection with Band Selection |
title_full |
Underwater Hyperspectral Target Detection with Band Selection |
title_fullStr |
Underwater Hyperspectral Target Detection with Band Selection |
title_full_unstemmed |
Underwater Hyperspectral Target Detection with Band Selection |
title_sort |
underwater hyperspectral target detection with band selection |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-03-01 |
description |
Compared to multi-spectral imagery, hyperspectral imagery has very high spectral resolution with abundant spectral information. In underwater target detection, hyperspectral technology can be advantageous in the sense of a poor underwater imaging environment, complex background, or protective mechanism of aquatic organisms. Due to high data redundancy, slow imaging speed, and long processing of hyperspectral imagery, a direct use of hyperspectral images in detecting targets cannot meet the needs of rapid detection of underwater targets. To resolve this issue, a fast, hyperspectral underwater target detection approach using band selection (BS) is proposed. It first develops a constrained-target optimal index factor (OIF) band selection (CTOIFBS) to select a band subset with spectral wavelengths specifically responding to the targets of interest. Then, an underwater spectral imaging system integrated with the best-selected band subset is constructed for underwater target image acquisition. Finally, a constrained energy minimization (CEM) target detection algorithm is used to detect the desired underwater targets. Experimental results demonstrate that the band subset selected by CTOIFBS is more effective in detecting underwater targets compared to the other three existing BS methods, uniform band selection (UBS), minimum variance band priority (MinV-BP), and minimum variance band priority with OIF (MinV-BP-OIF). In addition, the results also show that the acquisition and detection speed of the designed underwater spectral acquisition system using CTOIFBS can be significantly improved over the original underwater hyperspectral image system without BS. |
topic |
constrained-target optimal index factor band selection (ctoifbs) hyperspectral image underwater spectral imaging system underwater hyperspectral target detection band selection (bs) constrained energy minimization (cem) |
url |
https://www.mdpi.com/2072-4292/12/7/1056 |
work_keys_str_mv |
AT xianpingfu underwaterhyperspectraltargetdetectionwithbandselection AT xiaodishang underwaterhyperspectraltargetdetectionwithbandselection AT xudongsun underwaterhyperspectraltargetdetectionwithbandselection AT haoyangyu underwaterhyperspectraltargetdetectionwithbandselection AT meipingsong underwaterhyperspectraltargetdetectionwithbandselection AT cheinichang underwaterhyperspectraltargetdetectionwithbandselection |
_version_ |
1724941845822177280 |