SEGMENTING HYPERSPECTRAL IMAGES USING SPECTRAL CONVOLUTIONAL NEURAL NETWORKS IN THE PRESENCE OF NOISE

被引：3

作者：

Nalepa, Jakub ^{[1
,2
]}

Stanek, Marek ^{[1
]}

机构：

[1] Silesian Tech Univ, Akad 16, PL-44100 Gliwice, Poland

[2] KP Labs, Konarskiego 18C, PL-44100 Gliwice, Poland

来源：

IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2020年

关键词：

Hyperspectral imaging; noise; deep learning; classification; segmentation;

D O I：

10.1109/IGARSS39084.2020.9324198

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hyperspectrometers capture detailed information about the scanned objects, but they are susceptible to the presence of various kinds of noise. In this work, we quantify the impact of different levels of Gaussian and impulsive noise on the abilities of a spectral convolutional neural network applied for hyperspectral image segmentation. Our experiments showed that the noise may degrade the classification accuracy of the spectral convolutional nets, and can be a serious obstacle in deploying such models on-board a satellite, where the presence of noise is inevitable.

引用

页码：870 / 873

页数：4

共 50 条

[1] Spectral-spatial classification of hyperspectral images using deep convolutional neural networks
Yue, Jun
Zhao, Wenzhi
Mao, Shanjun
Liu, Hui
[J]. REMOTE SENSING LETTERS, 2015, 6 (06) : 468 - 477
[2] Segmentation of hyperspectral images using quantized convolutional neural networks
Lorenzo, Pablo Ribalta
Marcinkiewicz, Michal
Nalepa, Jakub
[J]. 2018 21ST EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD 2018), 2018, : 260 - 267
[3] CLASSIFICATION OF HYPERSPECTRAL COLON CANCER IMAGES USING CONVOLUTIONAL NEURAL NETWORKS
Mobilia, Sean
Sirkeci-Mergen, Birsen
Deal, Joshua
Rich, Thomas C.
Leavesley, Silas J.
[J]. 2019 IEEE DATA SCIENCE WORKSHOP (DSW), 2019, : 232 - 236
[4] HyperConv: spatio-spectral classification of hyperspectral images with deep convolutional neural networks
Ko, Seyoon
Jun, Goo
Won, Joong-Ho
[J]. KOREAN JOURNAL OF APPLIED STATISTICS, 2016, 29 (05) : 859 - 872
[5] Use of convolutional neural networks for segmenting images of roads from satellite
Seliverstov, Ya A.
Seliverstov, S. A.
Naryshkin, R. S.
Kripak, M. N.
[J]. INTERNATIONAL CONFERENCE ON MODERN TRENDS IN MANUFACTURING TECHNOLOGIES AND EQUIPMENT (ICMTMTE) 2020, 2020, 971
[6] Convolutional neural network for spectral–spatial classification of hyperspectral images
Hongmin Gao
Yao Yang
Chenming Li
Xiaoke Zhang
Jia Zhao
Dan Yao
[J]. Neural Computing and Applications, 2019, 31 : 8997 - 9012
[7] HYPERSPECTRAL IMAGE CLASSIFICATION USING SPECTRAL-SPATIAL CONVOLUTIONAL NEURAL NETWORKS
Nalepa, Jakub
Tulczyjew, Lukasz
Myller, Michal
Kawulok, Michal
[J]. IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 866 - 869
[8] Pixel-Based Classification of Hyperspectral Images Using Convolutional Neural Networks
Syed Aamer Hussain
Ali Tahir
Junaid Aziz Khan
Ahmad Salman
[J]. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2019, 87 : 33 - 45
[9] Pixel-Based Classification of Hyperspectral Images Using Convolutional Neural Networks
Hussain, Syed Aamer
Tahir, Ali
Khan, Junaid Aziz
Salman, Ahmad
[J]. PFG-JOURNAL OF PHOTOGRAMMETRY REMOTE SENSING AND GEOINFORMATION SCIENCE, 2019, 87 (1-2): : 33 - 45
[10] Spectral Classification of a Set of Hyperspectral Images using the Convolutional Neural Network, in a Single Training
Zbakh, Abdelali
Mdaghri, Zoubida Alaoui
Benyoussef, Abdelillah
El Kenz, Abdellah
El Yadari, Mourad
[J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (06) : 245 - 250

← 1 2 3 4 5 →