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

Abstract

Hyperspectral image classification has become a hot research topic. HSI has been widely used in a wide range of realworld 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 Hyperspectral Image Classification (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 the 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 costconsuming. As a result, this survey describes some methodologies for improving the classification performance of DL techniques, which can serve as future recommendations.

A Novel Levy Walk-Based Framework for Scheduling Power-Intensive Mobile Edge Computing Tasks

“…Within a CNN, convolutions are typically integrated into specific layers referred to as convolutional layers [31]. These layers are composed of multiple filters, each responsible for detecting distinct patterns in the input data [139]- [146]. During the training phase, the model goes through the process of backpropagation and gradient descent to learn the optimal weights of the convolutional filters.…”

Spectral–Spatial Graph Convolutional Network with Dynamic-Synchronized Multiscale Features for Few-Shot Hyperspectral Image Classification

“…Based on these, the HSI has been widely used in various fields [1][2][3], including agriculture, land-cover classification, forestry, urban planning, national defense, and medical diagnostic imaging. Currently, the HSI classification has drawn broad attention in the field of remote sensing [4].…”

“…The key to addressing the above problems is considered as extracting sufficiently discriminative features. By exploiting deeper features with the rich discriminative information, deep learning (DL) has been widely applied for HSI classification [4]. The representative models include the stacked autoencoder (SAE) [17], recurrent neural network (RNN) [18,19], convolutional neural network (CNN) [20], deep belief network (DBN) [21], generative adversarial networks (GAN) [22], and long short-term memory (LSTM) [23].…”