Abstract
| Original language | English |
|---|---|
| Number of pages | 6 |
| Publication status | Published - 26 Nov 2018 |
| Event | 7th European Workshop on Visual Information Processing - Tampere, Finland Duration: 26 Nov 2018 → 28 Nov 2018 |
Conference
| Conference | 7th European Workshop on Visual Information Processing |
|---|---|
| Abbreviated title | EUVIP |
| Country | Finland |
| City | Tampere |
| Period | 26/11/18 → 28/11/18 |
Fingerprint
Keywords
- hyperspectral imaging
- autoencoder
- band selection
Cite this
}
Segmented autoencoders for unsupervised embedded hyperspectral band selection. / Tschannerl, Julius; Ren, Jinchang; Zabalza, Jaime; Marshall, Stephen.
2018. Paper presented at 7th European Workshop on Visual Information Processing, Tampere, Finland.Research output: Contribution to conference › Paper
TY - CONF
T1 - Segmented autoencoders for unsupervised embedded hyperspectral band selection
AU - Tschannerl, Julius
AU - Ren, Jinchang
AU - Zabalza, Jaime
AU - Marshall, Stephen
N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
PY - 2018/11/26
Y1 - 2018/11/26
N2 - One of the major challenges in hyperspectral imaging (HSI) is the selection of the most informative wavelengths within the vast amount of data in a hypercube. Band selection can reduce the amount of data and computational cost as well as counteracting the negative effects of redundant and erroneous information. In this paper, we propose an unsupervised, embedded band selection algorithm that utilises the deep learning framework. Autoencoders are used to reconstruct measured spectral signatures. By putting a sparsity constraint on the input weights, the bands that contribute most to the reconstruction can be identified and chosen as the selected bands. Additionally, segmenting the input data into several spectral regions and distributing the number of desired bands according to a density measure among these segments, the quality of the selected bands can be increased and the computational time reduced by training several autoencoders. Results on a benchmark remote sensing HSI dataset show that the proposed algorithm improves classification accuracy compared to other state of the art band selection algorithms and thereby builds the basis for a framework of embedded band selection in HSI.
AB - One of the major challenges in hyperspectral imaging (HSI) is the selection of the most informative wavelengths within the vast amount of data in a hypercube. Band selection can reduce the amount of data and computational cost as well as counteracting the negative effects of redundant and erroneous information. In this paper, we propose an unsupervised, embedded band selection algorithm that utilises the deep learning framework. Autoencoders are used to reconstruct measured spectral signatures. By putting a sparsity constraint on the input weights, the bands that contribute most to the reconstruction can be identified and chosen as the selected bands. Additionally, segmenting the input data into several spectral regions and distributing the number of desired bands according to a density measure among these segments, the quality of the selected bands can be increased and the computational time reduced by training several autoencoders. Results on a benchmark remote sensing HSI dataset show that the proposed algorithm improves classification accuracy compared to other state of the art band selection algorithms and thereby builds the basis for a framework of embedded band selection in HSI.
KW - hyperspectral imaging
KW - autoencoder
KW - band selection
UR - http://www.tut.fi/euvip2018/index.html
M3 - Paper
ER -