Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network

In recent years, the deep neural network has shown a strong presence in classification tasks and its effectiveness has been well proved. However, the framework of DNN usually requires a large number of samples. Compared to the training sets in classification tasks, the training sets for the target d...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yanlong Gao, Yan Feng, Xumin Yu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/84a7aae24c4041d7bdd46d2c7e54e0d2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:84a7aae24c4041d7bdd46d2c7e54e0d2
record_format dspace
spelling oai:doaj.org-article:84a7aae24c4041d7bdd46d2c7e54e0d22021-11-11T18:57:34ZHyperspectral Target Detection with an Auxiliary Generative Adversarial Network10.3390/rs132144542072-4292https://doaj.org/article/84a7aae24c4041d7bdd46d2c7e54e0d22021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4454https://doaj.org/toc/2072-4292In recent years, the deep neural network has shown a strong presence in classification tasks and its effectiveness has been well proved. However, the framework of DNN usually requires a large number of samples. Compared to the training sets in classification tasks, the training sets for the target detection of hyperspectral images may only include a few target spectra which are quite limited and precious. The insufficient labeled samples make the DNN-based hyperspectral target detection task a challenging problem. To address this problem, we propose a hyperspectral target detection approach with an auxiliary generative adversarial network. Specifically, the training set is first expanded by generating simulated target spectra and background spectra using the generative adversarial network. Then, a classifier which is highly associated with the discriminator of the generative adversarial network is trained based on the real and the generated spectra. Finally, in order to further suppress the background, guided filters are utilized to improve the smoothness and robustness of the detection results. Experiments conducted on real hyperspectral images show the proposed approach is able to perform more efficiently and accurately compared to other target detection approaches.Yanlong GaoYan FengXumin YuMDPI AGarticlehyperspectral imagestarget detectiongenerative adversarial networkScienceQENRemote Sensing, Vol 13, Iss 4454, p 4454 (2021)
institution DOAJ
collection DOAJ
language EN
topic hyperspectral images
target detection
generative adversarial network
Science
Q
spellingShingle hyperspectral images
target detection
generative adversarial network
Science
Q
Yanlong Gao
Yan Feng
Xumin Yu
Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
description In recent years, the deep neural network has shown a strong presence in classification tasks and its effectiveness has been well proved. However, the framework of DNN usually requires a large number of samples. Compared to the training sets in classification tasks, the training sets for the target detection of hyperspectral images may only include a few target spectra which are quite limited and precious. The insufficient labeled samples make the DNN-based hyperspectral target detection task a challenging problem. To address this problem, we propose a hyperspectral target detection approach with an auxiliary generative adversarial network. Specifically, the training set is first expanded by generating simulated target spectra and background spectra using the generative adversarial network. Then, a classifier which is highly associated with the discriminator of the generative adversarial network is trained based on the real and the generated spectra. Finally, in order to further suppress the background, guided filters are utilized to improve the smoothness and robustness of the detection results. Experiments conducted on real hyperspectral images show the proposed approach is able to perform more efficiently and accurately compared to other target detection approaches.
format article
author Yanlong Gao
Yan Feng
Xumin Yu
author_facet Yanlong Gao
Yan Feng
Xumin Yu
author_sort Yanlong Gao
title Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
title_short Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
title_full Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
title_fullStr Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
title_full_unstemmed Hyperspectral Target Detection with an Auxiliary Generative Adversarial Network
title_sort hyperspectral target detection with an auxiliary generative adversarial network
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/84a7aae24c4041d7bdd46d2c7e54e0d2
work_keys_str_mv AT yanlonggao hyperspectraltargetdetectionwithanauxiliarygenerativeadversarialnetwork
AT yanfeng hyperspectraltargetdetectionwithanauxiliarygenerativeadversarialnetwork
AT xuminyu hyperspectraltargetdetectionwithanauxiliarygenerativeadversarialnetwork
_version_ 1718431656734359552