Dual-Channel Densenet for Hyperspectral Image Classification

Yang, Gefei; Gewali, Utsav B.; Ientilucci, Emmett; Gartley, Micheal; Monteiro, Sildomar T.

doi:10.1109/IGARSS.2018.8517520

Dual-Channel Densenet for Hyperspectral Image Classification

Journal Article · Mon Nov 05 04:00:00 EST 2018 · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online)

DOI:https://doi.org/10.1109/IGARSS.2018.8517520· OSTI ID:1581642

Yang, Gefei ^[1]; Gewali, Utsav B. ^[2]; Ientilucci, Emmett ^[2]; Gartley, Micheal ^[2]; Monteiro, Sildomar T. ^[2]

Rochester Inst. of Technology, Rochester, NY (United States); Rochester Institute of Technology
Rochester Inst. of Technology, Rochester, NY (United States)

Deep neural networks provide deep extracted features for image classification. As a high dimension data, hyperspectral image (HSI) feature extraction is unlike an RGB image whose feature representation could not be simply generated in the spatial domain. To take full advantage of HSI, a dualchannel convolutional neural network (CNN) is applied, 1D convolution for the spectral domain and 2D convolution for spatial domain. For pixel-wise classification of HSI, in our network model, one-dimensional customized DenseNet is for extracting the hierarchical spectral features and another customized DenseNet is applied to extract the hierarchical spatial-related feature. Furthermore, we experimentally tuned the several widen factors and dense-net growth rates to evaluate the impact of hyper-parameter. Furthermore, to compare our proposed method with HSI classification methods, we test other three DNNs based method in two real-world HSI dataset. The result demonstrated our approach outperformed the state-of-art method

Research Organization:: Rochester Inst. of Technology, Rochester, NY (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation (NA-20)

DOE Contract Number:: NA0002482

OSTI ID:: 1581642

Journal Information:: IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online), Journal Name: IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online) Vol. 2018; ISSN 2153-7003

Publisher:: IEEE

Country of Publication:: United States

Language:: English

References (11)

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach Zhao, Wenzhi; Du, Shihong IEEE Transactions on Geoscience and Remote Sensing, Vol. 54, Issue 8 https://doi.org/10.1109/TGRS.2016.2543748	journal	August 2016
Deep Convolutional Neural Networks for Hyperspectral Image Classification Hu, Wei; Huang, Yangyu; Wei, Li Journal of Sensors, Vol. 2015 https://doi.org/10.1155/2015/258619	journal	January 2015
Spectral–spatial classification of hyperspectral images using deep convolutional neural networks Yue, Jun; Zhao, Wenzhi; Mao, Shanjun Remote Sensing Letters, Vol. 6, Issue 6 https://doi.org/10.1080/2150704X.2015.1047045	journal	May 2015
SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images Tarabalka, Yuliya; Fauvel, Mathieu; Chanussot, Jocelyn IEEE Geoscience and Remote Sensing Letters, Vol. 7, Issue 4 https://doi.org/10.1109/LGRS.2010.2047711	journal	October 2010
Deep residual networks for hyperspectral image classification Zhong, Zilong; Li, Jonathan; Ma, Lingfei 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) https://doi.org/10.1109/IGARSS.2017.8127330	conference	July 2017
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2016.90	conference	June 2016
Advances in Spectral-Spatial Classification of Hyperspectral Images Fauvel, M.; Tarabalka, Y.; Benediktsson, J. A. Proceedings of the IEEE, Vol. 101, Issue 3 https://doi.org/10.1109/JPROC.2012.2197589	journal	March 2013
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification Liu, Qingshan; Zhou, Feng; Hang, Renlong Remote Sensing, Vol. 9, Issue 12 https://doi.org/10.3390/rs9121330	journal	December 2017
Spectral angle based unary energy functions for spatial-spectral hyperspectral classification using Markov random fields Gewali, Utsav B.; Monteiro, Sildomar T. 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) https://doi.org/10.1109/WHISPERS.2016.8071716	conference	August 2016
A survey of image classification methods and techniques for improving classification performance Lu, D.; Weng, Q. International Journal of Remote Sensing, Vol. 28, Issue 5 https://doi.org/10.1080/01431160600746456	journal	March 2007
Learning Conditional Random Fields for Classification of Hyperspectral Images No authors listed IEEE Transactions on Image Processing, Vol. 19, Issue 7 https://doi.org/10.1109/TIP.2010.2045034	journal	July 2010

Similar Records

Deep Learning for Land Cover Classification Using Only a Few Bands

Journal Article · Sun Jun 21 20:00:00 EDT 2020 · Remote Sensing · OSTI ID:1668678

Digital Signal Processing Using Deep Neural Networks

Technical Report · Sat Apr 01 00:00:00 EDT 2023 · OSTI ID:1984848

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Journal Article · Wed May 18 20:00:00 EDT 2022 · Annals of Nuclear Energy · OSTI ID:1976818

Related Subjects

97 MATHEMATICS AND COMPUTING
Dual channel DenseNet
Hyperspectral Image classification
spatial
spectral

Dual-Channel Densenet for Hyperspectral Image Classification

Citation Formats

References (11)

Similar Records

Related Subjects