BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Santara, Anirban

Deep learning based land cover classification algorithms have recently been proposed in the literature. In hyperspectral images (HSIs), they face the challenges of large dimensionality, spatial variability of spectral signatures, and scarcity of labeled data. In this paper, we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs land cover classification. The architecture has fewer independent connection weights and thus requires fewer training samples. The method is found to outperform the highest reported accuracies on popular HSI data sets.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Santara, Anirban

Deep learning based land cover classification algorithms have recently been proposed in the literature. In hyperspectral images (HSIs), they face the challenges of large dimensionality, spatial variability of spectral signatures, and scarcity of labeled data. In this paper, we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs land cover classification. The architecture has fewer independent connection weights and thus requires fewer training samples. The method is found to outperform the highest reported accuracies on popular HSI data sets.

BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Santara, Anirban

Deep learning based land cover classification algorithms have recently been proposed in the literature. In hyperspectral images (HSIs), they face the challenges of large dimensionality, spatial variability of spectral signatures, and scarcity of labeled data. In this paper, we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs land cover classification. The architecture has fewer independent connection weights and thus requires fewer training samples. The method is found to outperform the highest reported accuracies on popular HSI data sets.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Document information

Title:

BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Contributors:

Santara, Anirban (author) / Mani, Kaustubh / Hatwar, Pranoot / Singh, Ankit / Garg, Ankur / Padia, Kirti / Mitra, Pabitra

Published in:

IEEE transactions on geoscience and remote sensing ; 55

Publication date:

2017

ISSN:

DOI:

https://doi.org/10.1109/TGRS.2017.2705073

Type of media:

Article (Journal)

Type of material:

Print

Language:

English

Keywords:

Fernerkundung , Messtechnik , Zeitschrift , Elektronik , Geowissenschaften

Classification:

Local classification TIB: 770/3710/5670
BKL: 38.03 Methoden und Techniken der Geowissenschaften / 74.41 Luftaufnahmen, Photogrammetrie

Similar titles

Spectral-Spatial Constraint Hyperspectral Image Classification

Ji, R | Online Contents | 2014

Spectral-spatial hyperspectral image classification via multiscale adaptive sparse representation

Fang, Leyuan | Online Contents | 2014

Spectral-Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach

Zhao, Wenzhi | Online Contents | 2016

Multiple Feature Learning for Hyperspectral Image Classification

Jun Li | Online Contents | 2015

Class-Specific Sparse Multiple Kernel Learning for Spectral–Spatial Hyperspectral Image Classification

Liu, Tianzhu | Online Contents | 2016