Dimensionality reduction techniques with HydraNet framework for HSI classification

Mohammed Q. Alkhatib; Mina Al-Saad; Nour Aburaed; Saeed Al Mansoori; Hussain Al Ahmad

doi:10.1109/ICIP46576.2022.9897740

Dimensionality reduction techniques with HydraNet framework for HSI classification

Mohammed Q. Alkhatib^*, Mina Al-Saad, Nour Aburaed, Saeed Al Mansoori, Hussain Al Ahmad

^*Corresponding author for this work

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

22 Downloads (Pure)

Abstract

Hyperspectral Imagery (HSI) classification is an important research area in remote sensing community due to its high efficiency in accurately analyzing ground features by assigning a class label to each pixel. This paper explores the use of Band Subset selection (BSS) methods as Dimensionality Reduction (DR) pre-processing stage for HSI classification, and compares them to Principal Component Analysis (PCA) approach. BSS is the problem of selecting the most independent bands in HSI cube. Classification is then performed using a proposed multi-branch HydraNet model that combines 1D, 2D, and 3D convolution. HydraNet is trained and tested using the benchmark Pavia University dataset, and the results are evaluated using Kappa and Overall Accuracy. Experimental results show positive indications of the network's performance, especially when compared to other state-of-the-art CNN networks.

Original language	English
Title of host publication	2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	3151-3155
Number of pages	5
ISBN (Electronic)	9781665496209
ISBN (Print)	9781665496216
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897740
Publication status	Published - 18 Oct 2022
Event	29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France Duration: 16 Oct 2022 → 19 Oct 2022

Conference

Conference	29th IEEE International Conference on Image Processing, ICIP 2022
Country/Territory	France
City	Bordeaux
Period	16/10/22 → 19/10/22

Keywords

band subset selection
dimensionality reduction
HSI classification
HydraNet

Access to Document

10.1109/ICIP46576.2022.9897740

Alkhatib-etal-IEEE-2022-Dimensionality-reduction-techniques-with-HydraNet-frameworkAccepted author manuscript, 1.18 MBLicence: Strath_1

Cite this

@inproceedings{f5d644317ecb4425a28fafdbdb8c7566,

title = "Dimensionality reduction techniques with HydraNet framework for HSI classification",

abstract = "Hyperspectral Imagery (HSI) classification is an important research area in remote sensing community due to its high efficiency in accurately analyzing ground features by assigning a class label to each pixel. This paper explores the use of Band Subset selection (BSS) methods as Dimensionality Reduction (DR) pre-processing stage for HSI classification, and compares them to Principal Component Analysis (PCA) approach. BSS is the problem of selecting the most independent bands in HSI cube. Classification is then performed using a proposed multi-branch HydraNet model that combines 1D, 2D, and 3D convolution. HydraNet is trained and tested using the benchmark Pavia University dataset, and the results are evaluated using Kappa and Overall Accuracy. Experimental results show positive indications of the network's performance, especially when compared to other state-of-the-art CNN networks.",

keywords = "band subset selection, dimensionality reduction, HSI classification, HydraNet",

author = "Alkhatib, {Mohammed Q.} and Mina Al-Saad and Nour Aburaed and {Al Mansoori}, Saeed and {Al Ahmad}, Hussain",

note = "{\textcopyright} 2022 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.; 29th IEEE International Conference on Image Processing, ICIP 2022 ; Conference date: 16-10-2022 Through 19-10-2022",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/ICIP46576.2022.9897740",

language = "English",

isbn = "9781665496216",

pages = "3151--3155",

booktitle = "2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings",

publisher = "IEEE",

}

Alkhatib, MQ, Al-Saad, M, Aburaed, N, Al Mansoori, S & Al Ahmad, H 2022, Dimensionality reduction techniques with HydraNet framework for HSI classification. in 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings. IEEE, Piscataway, NJ, pp. 3151-3155, 29th IEEE International Conference on Image Processing, ICIP 2022, Bordeaux, France, 16/10/22. https://doi.org/10.1109/ICIP46576.2022.9897740

TY - GEN

T1 - Dimensionality reduction techniques with HydraNet framework for HSI classification

AU - Alkhatib, Mohammed Q.

AU - Al-Saad, Mina

AU - Aburaed, Nour

AU - Al Mansoori, Saeed

AU - Al Ahmad, Hussain

N1 - © 2022 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 - 2022/10/18

Y1 - 2022/10/18

N2 - Hyperspectral Imagery (HSI) classification is an important research area in remote sensing community due to its high efficiency in accurately analyzing ground features by assigning a class label to each pixel. This paper explores the use of Band Subset selection (BSS) methods as Dimensionality Reduction (DR) pre-processing stage for HSI classification, and compares them to Principal Component Analysis (PCA) approach. BSS is the problem of selecting the most independent bands in HSI cube. Classification is then performed using a proposed multi-branch HydraNet model that combines 1D, 2D, and 3D convolution. HydraNet is trained and tested using the benchmark Pavia University dataset, and the results are evaluated using Kappa and Overall Accuracy. Experimental results show positive indications of the network's performance, especially when compared to other state-of-the-art CNN networks.

AB - Hyperspectral Imagery (HSI) classification is an important research area in remote sensing community due to its high efficiency in accurately analyzing ground features by assigning a class label to each pixel. This paper explores the use of Band Subset selection (BSS) methods as Dimensionality Reduction (DR) pre-processing stage for HSI classification, and compares them to Principal Component Analysis (PCA) approach. BSS is the problem of selecting the most independent bands in HSI cube. Classification is then performed using a proposed multi-branch HydraNet model that combines 1D, 2D, and 3D convolution. HydraNet is trained and tested using the benchmark Pavia University dataset, and the results are evaluated using Kappa and Overall Accuracy. Experimental results show positive indications of the network's performance, especially when compared to other state-of-the-art CNN networks.

KW - band subset selection

KW - dimensionality reduction

KW - HSI classification

KW - HydraNet

U2 - 10.1109/ICIP46576.2022.9897740

DO - 10.1109/ICIP46576.2022.9897740

M3 - Conference contribution book

AN - SCOPUS:85146695414

SN - 9781665496216

SP - 3151

EP - 3155

BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings

PB - IEEE

CY - Piscataway, NJ

T2 - 29th IEEE International Conference on Image Processing, ICIP 2022

Y2 - 16 October 2022 through 19 October 2022

ER -

Dimensionality reduction techniques with HydraNet framework for HSI classification

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this