Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser

Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser

Hyperspectral imaging (HSI) technology is able to provide fine spectral and spatial information of objects. It has the ability to discriminate materials and thereby has been used in a wide range of areas. However, traditional HSI strongly depends on the sunlight and hence is restricted to daytime. I...

Full description

Bibliographic Details
Main Authors: Yu Liu, Zilong Tao, Jun Zhang, Hao Hao, Yuanxi Peng, Jing Hou, Tian Jiang
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Applied Sciences
Subjects:
active hyperspectral imaging
supercontinuum laser
classification
deep-learning
Online Access:https://www.mdpi.com/2076-3417/10/9/3088
id doaj-7d1e13cbff724662b97b1c3bb81b55dd
record_format Article
spelling doaj-7d1e13cbff724662b97b1c3bb81b55dd2020-11-25T02:22:56ZengMDPI AGApplied Sciences2076-34172020-04-01103088308810.3390/app10093088Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum LaserYu Liu0Zilong Tao1Jun Zhang2Hao Hao3Yuanxi Peng4Jing Hou5Tian Jiang6College of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of High-Performance Computing, College of Computer, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of High-Performance Computing, College of Computer, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of High-Performance Computing, College of Computer, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of High-Performance Computing, College of Computer, National University of Defense Technology, Changsha 410073, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaCollege of Advanced Interdisciplinary Studies, National University of Defense Technology, Changsha 410073, ChinaHyperspectral imaging (HSI) technology is able to provide fine spectral and spatial information of objects. It has the ability to discriminate materials and thereby has been used in a wide range of areas. However, traditional HSI strongly depends on the sunlight and hence is restricted to daytime. In this paper, a visible/near-infrared active HSI classification method illuminated by a visible/near-infrared supercontinuum laser is developed for spectra detection and objects imaging in the dark. Besides, a deep-learning-based classifier, hybrid DenseNet, is created to learn the feature representations of spectral and spatial information parallelly from active HSI data and is used for the active HSI classification. By applying the method to a selection of objects in the dark successfully, we demonstrate that with the active HSI classification method, it is possible to detect objects of interest in practical applications. Correct active HSI classification of different objects further supports the viability of the method for camouflage detection, biomedical alteration detection, cave painting mapping and so on.https://www.mdpi.com/2076-3417/10/9/3088active hyperspectral imagingsupercontinuum laserclassificationdeep-learning
collection DOAJ
language English
format Article
sources DOAJ
author Yu Liu
Zilong Tao
Jun Zhang
Hao Hao
Yuanxi Peng
Jing Hou
Tian Jiang
spellingShingle Yu Liu
Zilong Tao
Jun Zhang
Hao Hao
Yuanxi Peng
Jing Hou
Tian Jiang
Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
Applied Sciences
active hyperspectral imaging
supercontinuum laser
classification
deep-learning
author_facet Yu Liu
Zilong Tao
Jun Zhang
Hao Hao
Yuanxi Peng
Jing Hou
Tian Jiang
author_sort Yu Liu
title Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
title_short Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
title_full Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
title_fullStr Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
title_full_unstemmed Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser
title_sort deep-learning-based active hyperspectral imaging classification method illuminated by the supercontinuum laser
publisher MDPI AG
series Applied Sciences
issn 2076-3417
publishDate 2020-04-01
description Hyperspectral imaging (HSI) technology is able to provide fine spectral and spatial information of objects. It has the ability to discriminate materials and thereby has been used in a wide range of areas. However, traditional HSI strongly depends on the sunlight and hence is restricted to daytime. In this paper, a visible/near-infrared active HSI classification method illuminated by a visible/near-infrared supercontinuum laser is developed for spectra detection and objects imaging in the dark. Besides, a deep-learning-based classifier, hybrid DenseNet, is created to learn the feature representations of spectral and spatial information parallelly from active HSI data and is used for the active HSI classification. By applying the method to a selection of objects in the dark successfully, we demonstrate that with the active HSI classification method, it is possible to detect objects of interest in practical applications. Correct active HSI classification of different objects further supports the viability of the method for camouflage detection, biomedical alteration detection, cave painting mapping and so on.
topic active hyperspectral imaging
supercontinuum laser
classification
deep-learning
url https://www.mdpi.com/2076-3417/10/9/3088
work_keys_str_mv AT yuliu deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT zilongtao deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT junzhang deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT haohao deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT yuanxipeng deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT jinghou deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
AT tianjiang deeplearningbasedactivehyperspectralimagingclassificationmethodilluminatedbythesupercontinuumlaser
_version_ 1724861007877111808

Similar Items