Adaptive Batch Extraction for Hyperspectral Image Classification Based on Convolutional Neural Network (original) (raw)
Related papers
Deep Learning Based Hyperspectral Image Classification: A Review For Future Enhancement
International journal of computing and digital system/International Journal of Computing and Digital Systems, 2024
The use of Hyperspectral Image(HSI) has become prevalent in many sectors due to its ability to identify detailed spectral information (i.e., relationships between the collected spectral data and the object in the HSI data) that cannot be obtained through ordinary imaging. Traditional RGB image classification approaches are insufficient for hyperspectral image classification(HSIC) because they struggle to capture the subtle spectral information that exists within hyperspectral data. In the past few years, the Deep Learning(DL) based model has become a very powerful and efficient non-linear feature extractor for a wide range of computer vision tasks. Furthermore, DL-based models are exempt from manual feature extraction. The use of this stimulus prompted the researchers to use a DL-based model for the classification of Hyperspectral Images, which yielded impressive results. This motivation inspired the researchers to develop a DL-based model for the classification of hyperspectral images, which performed well. Deeper networks might encounter vanishing gradient problems, making optimization more difficult. To address this issue, regularisation and architectural improvements are being implemented. One of the key issues is that the DL-based HSIC model requires a large number of training samples for training, which is an important concern with hyperspectral data due to the scarcity of public HSI datasets. This article provides an overview of deep learning for hyperspectral image classification and assesses the most recent methods. Among all studied methods SpectralNET offers significantly better performance, due to the utilization of wavelet transformation.
Deep Learning for Hyperspectral Image Classification: An Overview
IEEE Transactions on Geoscience and Remote Sensing, 2019
Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework which divides the corresponding works into spectralfeature networks, spatial-feature networks, and spectral-spatialfeature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.
Hyperspectral Satellite Image Classification using Deep Learning
TEST Engineering & Management, 2020
Hyperspectral images are utilized to provide adequate spectral information so as to acknowledge and differentiate spectrally distinctive materials. Optical analysis techniques are utilized to detect and identify the objects from a scale of images. Hyperspectral imaging technique is one among them. Hyperspectral image classification research is an intense field of study and an outsized number ofrecent approacheshave been developed to enhance the performance for specific applications that exploit both spatial and spectral image content. The goal of hyperspectral imaging is to obtain the spectrum for each and every pixel within the image of a scene, with the intent of detecting processes, identifying materials or finding objects. In this particular study, a strategy for the classification of Hyperspectral satellite images is asserted using deep learning framework. Thisframeworkinvolves inception module architecture containing 1x1, 3x3 and 5x5Convolutional layers which gives an overallclassification accuracy of 97.30%.
Hyperspectral Image Analysis using Deep Learning -a Review
Deep learning is a rather new approach to machine learning that has achieved remarkable results in a large number of different image processing applications. Lately, application of deep learning to detect and classify spectral and spatio-spectral signatures in hyperspectral images has emerged. The high dimensionality of hyperspectral images and the limited amount of labelled training data makes deep learning an appealing approach for analysing hyperspectral data. Auto-Encoder can be used to learn a hierarchical feature representation using solely unlabelled data, the learnt representation can be combined with a logistic regression classifier to achieve results in-line with existing state-of-the-art methods. In this paper, we compare results between a set of available publications and find that deep learning perform in line with state-of-the-art on many data sets but little evidence exists that deep learning outperform the reference methods.
Feature Extraction and Classification of Hyperspectral Images Using Hierarchical Network
IEEE Geoscience and Remote Sensing Letters, 2019
In recent years, researchers have frequently utilized convolutional neural networks (CNNs) to classify hyperspectral images and have, indeed, embraced exciting achievements. However, most of the existing approaches tend to handle images block by block, which is less efficient as image blocks need to be fed into the network for many times. With this in mind, this letter presents a novel hierarchical CNN that adopts raw images as the input and extracts useful features for classification. Specifically, we adopt several hierarchical convolutional neural layers as a feature extractor and adopt the support vector machine instead of the classifying layer in the original network as the final classifier. Experiments show the proposed approach can work efficiently and exhibit competitive performance when compared to some other approaches based on deep networks.
A SURVEY: DEEP LEARNING CLASSIFIERS FOR HYPERSPECTRAL IMAGE CLASSIFICATION
Journal of Theoretical and Applied Information Technology, 2021
Hyperspectral imaging (HSI) is a popular subject in remote sensing data processing because of the huge quantity of data included in these images, which enables for improved description and utilization of the surface of the earth by integrating abundant spectral and spatial data. However, due to the high dimensionality of HSI data and the limited number of labelled examples available, conducting HSI image classification poses significant technical and pragmatic hurdles. Approaches to HSI classification with deep learning have gained major successes in recent years as new deep learning algorithms emerge, giving unique prospects for hyperspectral image classification research and development. Initially, a quick introduction to standard deep learning (DL) models is provided, followed by a comparison of the performance of common DL based HSI approaches. Finally, the difficulties and future research prospects are explored.
Remote Sensing
Hyperspectral imaging is a rich source of data, allowing for a multitude of effective applications. However, such imaging remains challenging because of large data dimension and, typically, a small pool of available training examples. While deep learning approaches have been shown to be successful in providing effective classification solutions, especially for high dimensional problems, unfortunately they work best with a lot of labelled examples available. The transfer learning approach can be used to alleviate the second requirement for a particular dataset: first the network is pre-trained on some dataset with large amount of training labels available, then the actual dataset is used to fine-tune the network. This strategy is not straightforward to apply with hyperspectral images, as it is often the case that only one particular image of some type or characteristic is available. In this paper, we propose and investigate a simple and effective strategy of transfer learning that us...
Hyperspectral Image Classification - Traditional to Deep Models: A Survey for Future Prospects
ArXiv, 2021
Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, deep learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies of the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state...
Hyperspectral Image Classification with Convolutional Neural Networks
2015
Hyperspectral image (HSI) classification is one of the most widely used methods for scene analysis from hyperspectral imagery. In the past, many different engineered features have been proposed for the HSI classification problem. In this paper, however, we propose a feature learning approach for hyperspectral image classification based on convolutional neural networks (CNNs). The proposed CNN model is able to learn structured features, roughly resembling different spectral band-pass filters, directly from the hyperspectral input data. Our experimental results, conducted on a commonlyused remote sensing hyperspectral dataset, show that the proposed method provides classification results that are among the state-of-the-art, without using any prior knowledge or engineered features.
Journal of Electronic Imaging, 2022
In recent years, researchers have frequently utilized convolutional neural networks (CNNs) to classify hyperspectral images and have, indeed, embraced exciting achievements. However, most of the existing approaches tend to handle images block by block, which is less efficient as image blocks need to be fed into the network for many times. With this in mind, this letter presents a novel hierarchical CNN that adopts raw images as the input and extracts useful features for classification. Specifically, we adopt several hierarchical convolutional neural layers as a feature extractor and adopt the support vector machine instead of the classifying layer in the original network as the final classifier. Experiments show the proposed approach can work efficiently and exhibit competitive performance when compared to some other approaches based on deep networks.