Home > Research > Publications & Outputs > Fast Hyperspectral Band Selection Based on Spat...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Fast Hyperspectral Band Selection Based on Spatial Feature Extraction

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Fast Hyperspectral Band Selection Based on Spatial Feature Extraction. / Cao, Xianghai; Ji, Yamei; Wang, Lin et al.
In: Journal of Real-Time Image Processing, Vol. 15, No. 3, 10.2018, p. 555-564.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Cao, X, Ji, Y, Wang, L, Ji, B, Jiao, L & Han, J 2018, 'Fast Hyperspectral Band Selection Based on Spatial Feature Extraction', Journal of Real-Time Image Processing, vol. 15, no. 3, pp. 555-564. https://doi.org/10.1007/s11554-018-0777-9

APA

Cao, X., Ji, Y., Wang, L., Ji, B., Jiao, L., & Han, J. (2018). Fast Hyperspectral Band Selection Based on Spatial Feature Extraction. Journal of Real-Time Image Processing, 15(3), 555-564. https://doi.org/10.1007/s11554-018-0777-9

Vancouver

Cao X, Ji Y, Wang L, Ji B, Jiao L, Han J. Fast Hyperspectral Band Selection Based on Spatial Feature Extraction. Journal of Real-Time Image Processing. 2018 Oct;15(3):555-564. Epub 2018 Apr 27. doi: 10.1007/s11554-018-0777-9

Author

Cao, Xianghai ; Ji, Yamei ; Wang, Lin et al. / Fast Hyperspectral Band Selection Based on Spatial Feature Extraction. In: Journal of Real-Time Image Processing. 2018 ; Vol. 15, No. 3. pp. 555-564.

Bibtex

@article{8c451c414fe042ee9af72090c218d9f2,
title = "Fast Hyperspectral Band Selection Based on Spatial Feature Extraction",
abstract = "Hyperspectral images usually consist of hundreds of spectral bands, which can be used to precisely characterize different land cover types. However, the high dimensionality also has some disadvantages, such as the Hughes effect and a high storage demand. Band selection is an effective method to address these issues. However, most band selection algorithms are conducted with the high-dimensional band images, which will bring high computation complexity and may deteriorate the selection performance. In this paper, spatial feature extraction is used to reduce the dimensionality of band images and improve the band selection performance. The experiment results obtained on three real hyperspectral datasets confirmed that the spatial feature extraction-based approach exhibits more robust classification accuracy when compared with other methods. Besides, the proposed method can dramatically reduce the dimensionality of each band image, which makes it possible for band selection to be implemented in real time situations.",
keywords = "Hyperspectral image, Band selection, Spatial feature extraction ",
author = "Xianghai Cao and Yamei Ji and Lin Wang and Beibei Ji and Licheng Jiao and Jungong Han",
year = "2018",
month = oct,
doi = "10.1007/s11554-018-0777-9",
language = "English",
volume = "15",
pages = "555--564",
journal = "Journal of Real-Time Image Processing",
issn = "1861-8200",
publisher = "Springer Verlag",
number = "3",

}

RIS

TY - JOUR

T1 - Fast Hyperspectral Band Selection Based on Spatial Feature Extraction

AU - Cao, Xianghai

AU - Ji, Yamei

AU - Wang, Lin

AU - Ji, Beibei

AU - Jiao, Licheng

AU - Han, Jungong

PY - 2018/10

Y1 - 2018/10

N2 - Hyperspectral images usually consist of hundreds of spectral bands, which can be used to precisely characterize different land cover types. However, the high dimensionality also has some disadvantages, such as the Hughes effect and a high storage demand. Band selection is an effective method to address these issues. However, most band selection algorithms are conducted with the high-dimensional band images, which will bring high computation complexity and may deteriorate the selection performance. In this paper, spatial feature extraction is used to reduce the dimensionality of band images and improve the band selection performance. The experiment results obtained on three real hyperspectral datasets confirmed that the spatial feature extraction-based approach exhibits more robust classification accuracy when compared with other methods. Besides, the proposed method can dramatically reduce the dimensionality of each band image, which makes it possible for band selection to be implemented in real time situations.

AB - Hyperspectral images usually consist of hundreds of spectral bands, which can be used to precisely characterize different land cover types. However, the high dimensionality also has some disadvantages, such as the Hughes effect and a high storage demand. Band selection is an effective method to address these issues. However, most band selection algorithms are conducted with the high-dimensional band images, which will bring high computation complexity and may deteriorate the selection performance. In this paper, spatial feature extraction is used to reduce the dimensionality of band images and improve the band selection performance. The experiment results obtained on three real hyperspectral datasets confirmed that the spatial feature extraction-based approach exhibits more robust classification accuracy when compared with other methods. Besides, the proposed method can dramatically reduce the dimensionality of each band image, which makes it possible for band selection to be implemented in real time situations.

KW - Hyperspectral image

KW - Band selection

KW - Spatial feature extraction

U2 - 10.1007/s11554-018-0777-9

DO - 10.1007/s11554-018-0777-9

M3 - Journal article

VL - 15

SP - 555

EP - 564

JO - Journal of Real-Time Image Processing

JF - Journal of Real-Time Image Processing

SN - 1861-8200

IS - 3

ER -