A Multiscale Deep Learning Approach for High-Resolution Hyperspectral Image Classification (original) (raw)
Related papers
Deep learning has achieved great successes in conventional computer vision tasks. In this paper, we exploit deep learning techniques to address the hyperspectral image classification problem. In contrast to conventional computer vision tasks that only examine the spatial context, our proposed method can exploit both spatial context and spectral correlation to enhance hyperspectral image classification. In particular, we advocate four new deep learning models, namely 2D Convolutional neural network (2D-CNN), 3D Convolutional neural network (3D-CNN), recurrent 2D Convolutional neural network (R-2D-CNN), and recurrent 3D Convolutional neural network (R-3D-CNN) for hyperspectral image classification. We conducted rigorous experiments based on six publicly available data sets. Through a comparative evaluation with other state-of-the-art methods, our experimental results confirm the superiority of the proposed deep learning models, especially the R-3D-CNN and the R-2D-CNN deep learning models.
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.
Classification of Hyperspectral Imagery using Deep Learning
The classification of Hyperspectral Imagery (HSI) has been a focal point in pattern recognition, leading to diverse research outcomes. This study explores spectral-spatial information for classification, incorporating Deep Learning methodologies, and employing various models such as 3D Convolutional Neural Network (3DCNN), Graph Convolutional Network and Convolutional Neural Network (GCN+CNN), Autoencoder, Hyperspectral Vision Transformer (HVT), EarthMapper Toolbox, and Spectralformer. Each model is tailored to capture distinctive features and relationships within hyperspectral data. A comprehensive comparison reveals variations in performance across different classification tasks, considering spatial and spectral aspects, computational efficiency, and dataset characteristics. The study aims to guide practitioners in selecting suitable models based on specific application requirements. Future endeavors include integrating graph attention modules with Transformer networks and leveraging existing models for transfer learning on multispectral data in target domains. The results and insights presented contribute to the advancement of hyperspectral image classification methodologies
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.
Spectral-Spatial Classification of Hyperspectral Images with Multi-Level CNN
In recent years, deep learning methods have significantly increased the classification accuracy of remotely sensed images. However, most of the methods focus only on spectral information ignoring the spatial information, thus extracting only low-level features from a hyperspectral image. In this study, a multi-level 3-dimensional convolutional neural network (3-D CNN) has been proposed. The 3-D CNN serves the purpose of including both spatial and spectral information. The multi-level architecture consists of varying kernel sizes to extract features at different levels. This helps in distinguishing classes from multiple spatial scales and aspect ratios. We have evaluated the performance of the proposed approach on four standard hyperspectral datasets to verify the generalisation ability. Compared with other state-of-the-art methods, an improvement of 2% − 5% in overall accuracy and kappa coefficient has been observed. The effect of spatial window size on classification accuracy has b...
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%.
Multi-scale 3D-convolutional neural network for hyperspectral image classification
Indonesian Journal of Electrical Engineering and Computer Science
Deep Learning methods are state-of-the-art approaches for pixel-based hyperspectral images (HSI) classification. High classification accuracy has been achieved by extracting deep features from both spatial-spectral channels. However, the efficiency of such spatial-spectral approaches depends on the spatial dimension of each patch and there is no theoretically valid approach to find the optimum spatial dimension to be considered. It is more valid to extract spatial features by considering varying neighborhood scales in spatial dimensions. In this regard, this article proposes a deep convolutional neural network (CNN) model wherein three different multi-scale spatial-spectral patches are used to extract the features in both the spatial and spectral channels. In order to extract these potential features, the proposed deep learning architecture takes three patches various scales in spatial dimension. 3D convolution is performed on each selected patch and the process runs through entire ...
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.
Efficient Classification of Hyperspectral Data Using Deep Neural Network Model
Human-centric Computing and Information Sciences , 2022
In recent years, there has been tremendous progress in the classification of hyperspectral images (HSI) using a deep neural network. Due to the high complexity of spectral properties, limited ground truth samples, and extreme inhomogeneity of hyperspectral data, an efficient classification of HSI using deep convolutional neural networks remains difficult. As a result, the ever-increasing volume of data necessitates the effective categorization of remote sensor-based HSI utilizing advanced deep learning. Over time, certain deep learning models for learning to detect HSI have been developed, and many researchers have used convolutional neural networks (CNNs). Previous research on hyperspectral data categorization using deep learning models have faced the issue of performance degradation due to insufficient layer selection in the CNN, which is studied in this research. In our solution, we have proposed a CNN model for effectively classifying hyperspectral data using deep learning. We tested our method using land cover benchmark datasets and found that it outperforms the current state-of-the-art. When compared to conventional machine learning methods and baseline procedures, the results of this study reveal that using an upgraded CNN model significantly improves the performance (accuracy = 93.621, precision = 91.571, recall = 92, F1 score = 90.714).
Remote Sensing
Using ground-based, remote hyperspectral images from 0.4–1.0 micron in ∼850 spectral channels—acquired with the Urban Observatory facility in New York City—we evaluate the use of one-dimensional Convolutional Neural Networks (CNNs) for pixel-level classification and segmentation of built and natural materials in urban environments. We find that a multi-class model trained on hand-labeled pixels containing Sky, Clouds, Vegetation, Water, Building facades, Windows, Roads, Cars, and Metal structures yields an accuracy of 90–97% for three different scenes. We assess the transferability of this model by training on one scene and testing to another with significantly different illumination conditions and/or different content. This results in a significant (∼45%) decrease in the model precision and recall as does training on all scenes at once and testing on the individual scenes. These results suggest that while CNNs are powerful tools for pixel-level classification of very high-resolutio...