Zobraziť v EDS

Conventional to Deep Ensemble Methods for Hyperspectral Image Classification: A Comprehensive Survey

Uložené v:
Podrobná bibliografia
Názov: Conventional to Deep Ensemble Methods for Hyperspectral Image Classification: A Comprehensive Survey
Autori: Farhan Ullah, Irfan Ullah, Rehan Ullah Khan, Salabat Khan, Khalil Khan, Giovanni Pau
Zdroj: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 3878-3916 (2024)
Informácie o vydavateľovi: Institute of Electrical and Electronics Engineers (IEEE), 2024.
Rok vydania: 2024
Predmety: hyperspectral image classification (HSIC), deep ensemble, QC801-809, Convolutional neural network (CNN), Geophysics. Cosmic physics, 0211 other engineering and technologies, 02 engineering and technology, spectral features, 01 natural sciences, Ocean engineering, deep learning (DL), spatial features, TC1501-1800, 0105 earth and related environmental sciences
Popis: Hyperspectral image classification (HSIC) has become a hot research topic. Hyperspectral imaging (HSI) has been widely used in a wide range of real-world application areas due to the in-depth spectral information stored within each pixel. Noticeably, the detailed features, i.e., a nonlinear correlation between the obtained spectral data and the correlating HSI data object, generate efficient classification results that are complex for traditional techniques. Deep learning (DL) has recently been validated as an influential feature extractor that efficiently identifies the nonlinear issues that have arisen in various computer vision challenges. This motivates using DL for HSIC, which shows promising results. This survey provides a brief description of DL for HSIC and compares cutting-edge methodologies in the field. We will first summarize the key challenges for HSIC, and then, we will discuss the superiority of DL and DL ensemble in addressing these issues. In this article, we divide state-of-the-art DL methodologies and DL with ensemble into spectral features, spatial features, and combined spatial–spectral features in order to comprehensively and critically evaluate the progress (future research directions as well) of such methodologies for HSIC. Furthermore, we will take into account that DL involves a substantial percentage of labeled training images, whereas obtaining such a number for HSI is time and cost consuming. As a result, this survey describes some methodologies for improving the classification performance of DL techniques, which can serve as future recommendations.
Druh dokumentu: Article
ISSN: 2151-1535
1939-1404
DOI: 10.1109/jstars.2024.3353551
Prístupová URL adresa: https://doaj.org/article/25f303af24044db496dc610b716b9f6b
Rights: CC BY NC ND
Prístupové číslo: edsair.doi.dedup.....c092c665fc0c3db43272dd70cad1b043
Databáza: OpenAIRE
Popis
Abstrakt:Hyperspectral image classification (HSIC) has become a hot research topic. Hyperspectral imaging (HSI) has been widely used in a wide range of real-world application areas due to the in-depth spectral information stored within each pixel. Noticeably, the detailed features, i.e., a nonlinear correlation between the obtained spectral data and the correlating HSI data object, generate efficient classification results that are complex for traditional techniques. Deep learning (DL) has recently been validated as an influential feature extractor that efficiently identifies the nonlinear issues that have arisen in various computer vision challenges. This motivates using DL for HSIC, which shows promising results. This survey provides a brief description of DL for HSIC and compares cutting-edge methodologies in the field. We will first summarize the key challenges for HSIC, and then, we will discuss the superiority of DL and DL ensemble in addressing these issues. In this article, we divide state-of-the-art DL methodologies and DL with ensemble into spectral features, spatial features, and combined spatial–spectral features in order to comprehensively and critically evaluate the progress (future research directions as well) of such methodologies for HSIC. Furthermore, we will take into account that DL involves a substantial percentage of labeled training images, whereas obtaining such a number for HSI is time and cost consuming. As a result, this survey describes some methodologies for improving the classification performance of DL techniques, which can serve as future recommendations.
ISSN:21511535
19391404
DOI:10.1109/jstars.2024.3353551