Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.9
5.0
Journals
Remote Sensing
Special Issues
Deep Learning for Remote Sensing Image Classification
remotesensing-logo
Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Deep Learning for Remote Sensing Image Classification

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: closed (1 June 2022) | Viewed by 97796

Special Issue Editors

Dr. Sidike Paheding

E-Mail Website
Guest Editor
Department of Applied Computing, College of Computing, Michigan Technological University, 1400 Townsend Drive, Houghton, MI 49931, USA
Interests: deep learning; computer vision; remote sensing
Special Issues, Collections and Topics in MDPI journals
Dr. Zahangir Alom

E-Mail
Co-Guest Editor
University of Dayton, 300 College Park, Dayton, OH 45469, USA
Interests: Deep learning; computer vision; medical imaging and computational pathology
Dr. Maitiniyazi Maimaitijiang

E-Mail Website
Co-Guest Editor
Geospatial Institute, Saint Louis University, Des Peres Hall, 3694 West Pine Mall, St. Louis, MO 63108, USA
Interests: remote sensing; geospatial data analysis and deep learning
Special Issues, Collections and Topics in MDPI journals
Dr. Matthew Maimaitiyiming

E-Mail Website1 Website2
Co-Guest Editor
Division of Food Systems and Bioengineering, University of Missouri-Columbia, 256 WC Stringer Wing, Eckles Hall, Columbia, MO 65211, USA
Interests: remote sensing; spatial analystics; plant science and machine learning for predictive modelling
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, we have been witnessing the tremendous success of deep learning in diverse research areas and applications, ranging from natural language processing, healthcare, wide-area surveillance, network security, and precision agriculture. The significance of deep learning in remote sensing image analysis has also been observed and is continuously growing. Thanks to the rapid advancement of sensors, including high-resolution RGB, thermal, Lidar, and multi-/hyper-spectral cameras, and emerging sensing platforms such as satellites and aerial vehicles, remote sensing image scenes can now be captured by multi-temporal, multi-senor, and sensing devices with a wider view. These developments facilitate remote sensing research fields, but also introduce challenges such as 1) techniques for processing large quantities and wider areas of remote sensing image data, 2) high dimensional and noisy spectral and spatial information, and 3) the complexity of remote sensing scene itself. These challenges not only cause difficulties for image analytics and interpretation but also demands more advanced computational methods. Although many deep learning algorithms have been proposed to address some challenges, the problems remain. The objective of this Special Issue is to provide a forum for cutting-edge research works that address the ongoing challenges in remote sensing image classification. We welcome topics that include, but are not limited to the following:

  • Land-use land-cover mapping
  • Hyperspectral image classification
  • Data fusion technologies
  • High-performance computing paradigms for remote sensing image classification
  • Dimensionality reduction for remote sensing data
  • Spatial and spectral feature extraction methods
  • Big data analytics
  • Data visualization of classification results
  • Data augmentation for image classification
  • New image classification architectures
  • New datasets for remote sensing image classification with deep learning

Dr. Sidike Paheding
Dr. Zahangir Alom
Dr. Maitiniyazi Maimaitijiang
Dr. Matthew Maimaitiyiming
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Deep learning
  • Remote sensing
  • Computer vision
  • Adversarial learning
  • Geospatial data analysis
  • Scene classification
  • Convolutional neural networks (CNN)
  • Feature extraction
  • Dimensionality reduction
  • Aerial and satellite images

Published Papers (18 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

20 pages, 6419 KiB  
Article
Prob-POS: A Framework for Improving Visual Explanations from Convolutional Neural Networks for Remote Sensing Image Classification
by Xianpeng Guo, Biao Hou, Zitong Wu, Bo Ren, Shuang Wang and Licheng Jiao
Remote Sens. 2022, 14(13), 3042; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14133042 - 24 Jun 2022
Cited by 3 | Viewed by 1400
Abstract
During the past decades, convolutional neural network (CNN)-based models have achieved notable success in remote sensing image classification due to their powerful feature representation ability. However, the lack of explainability during the decision-making process is a common criticism of these high-capacity networks. Local [...] Read more.
During the past decades, convolutional neural network (CNN)-based models have achieved notable success in remote sensing image classification due to their powerful feature representation ability. However, the lack of explainability during the decision-making process is a common criticism of these high-capacity networks. Local explanation methods that provide visual saliency maps have attracted increasing attention as a means to surmount the barrier of explainability. However, the vast majority of research is conducted on the last convolutional layer, where the salient regions are unintelligible for partial remote sensing images, especially scenes that contain plentiful small targets or are similar to the texture image. To address these issues, we propose a novel framework called Prob-POS, which consists of the class-activation map based on the probe network (Prob-CAM) and the weighted probability of occlusion (wPO) selection strategy. The proposed probe network is a simple but effective architecture to generate elaborate explanation maps and can be applied to any layer of CNNs. The wPO is a quantified metric to evaluate the explanation effectiveness of each layer for different categories to automatically pick out the optimal explanation layer. Variational weights are taken into account to highlight the high-scoring regions in the explanation map. Experimental results on two publicly available datasets and three prevalent networks demonstrate that Prob-POS improves the faithfulness and explainability of CNNs on remote sensing images. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

16 pages, 2566 KiB  
Article
SAR Ship–Iceberg Discrimination in Arctic Conditions Using Deep Learning
by Peder Heiselberg, Kristian A. Sørensen, Henning Heiselberg and Ole B. Andersen
Remote Sens. 2022, 14(9), 2236; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14092236 - 06 May 2022
Cited by 14 | Viewed by 2133
Abstract
Maritime surveillance of the Arctic region is of growing importance as shipping, fishing and tourism are increasing due to the sea ice retreat caused by global warming. Ships that do not identify themselves with a transponder system, so-called dark ships, pose a security [...] Read more.
Maritime surveillance of the Arctic region is of growing importance as shipping, fishing and tourism are increasing due to the sea ice retreat caused by global warming. Ships that do not identify themselves with a transponder system, so-called dark ships, pose a security risk. They can be detected by SAR satellites, which can monitor the vast Arctic region through clouds, day and night, with the caveat that the abundant icebergs in the Arctic cause false alarms. We collect and analyze 200 Sentinel-1 horizontally polarized SAR scenes from areas with high maritime traffic and from the Arctic region with a high density of icebergs. Ships and icebergs are detected using a continuous wavelet transform, which is optimized by correlating ships to known AIS positions. Globally, we are able to assign 72% of the AIS signals to a SAR ship and 32% of the SAR ships to an AIS signal. The ships are used to construct an annotated dataset of more than 9000 ships and ten times as many icebergs. The dataset is used for training several convolutional neural networks, and we propose a new network which achieves state of the art performance compared to previous ship–iceberg discrimination networks, reaching 93% validation accuracy. Furthermore, we collect a smaller test dataset consisting of 424 ships from 100 Arctic scenes which are correlated to AIS positions. This dataset constitutes an operational Arctic test scenario. We find these ships harder to classify with a lower test accuracy of 83%, because some of the ships sail near icebergs and ice floes, which confuses the classification algorithms. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

27 pages, 7626 KiB  
Article
A Two-Branch Convolutional Neural Network Based on Multi-Spectral Entropy Rate Superpixel Segmentation for Hyperspectral Image Classification
by Caihong Mu, Zhidong Dong and Yi Liu
Remote Sens. 2022, 14(7), 1569; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14071569 - 24 Mar 2022
Cited by 10 | Viewed by 2826
Abstract
Convolutional neural networks (CNNs) can extract advanced features of joint spectral–spatial information, which are useful for hyperspectral image (HSI) classification. However, the patch-based neighborhoods of samples with fixed sizes are usually used as the input of the CNNs, which cannot dig out the [...] Read more.
Convolutional neural networks (CNNs) can extract advanced features of joint spectral–spatial information, which are useful for hyperspectral image (HSI) classification. However, the patch-based neighborhoods of samples with fixed sizes are usually used as the input of the CNNs, which cannot dig out the homogeneousness between the pixels within and outside of the patch. In addition, the spatial features are quite different in different spectral bands, which are not fully utilized by the existing methods. In this paper, a two-branch convolutional neural network based on multi-spectral entropy rate superpixel segmentation (TBN-MERS) is designed for HSI classification. Firstly, entropy rate superpixel (ERS) segmentation is performed on the image of each spectral band in an HSI, respectively. The segmented images obtained are stacked band by band, called multi-spectral entropy rate superpixel segmentation image (MERSI), and then preprocessed to serve as the input of one branch in TBN-MERS. The preprocessed HSI is used as the input of the other branch in TBN-MERS. TBN-MERS extracts features from both the HSI and the MERSI and then utilizes the fused spectral–spatial features for the classification of HSIs. TBN-MERS makes full use of the joint spectral–spatial information of HSIs at the scale of superpixels and the scale of neighborhood. Therefore, it achieves excellent performance in the classification of HSIs. Experimental results on four datasets demonstrate that the proposed TBN-MERS can effectively extract features from HSIs and significantly outperforms some state-of-the-art methods with a few training samples. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

29 pages, 15256 KiB  
Article
ClassHyPer: ClassMix-Based Hybrid Perturbations for Deep Semi-Supervised Semantic Segmentation of Remote Sensing Imagery
by Yongjun He, Jinfei Wang, Chunhua Liao, Bo Shan and Xin Zhou
Remote Sens. 2022, 14(4), 879; https://0-doi-org.brum.beds.ac.uk/10.3390/rs14040879 - 12 Feb 2022
Cited by 19 | Viewed by 3608
Abstract
Inspired by the tremendous success of deep learning (DL) and the increased availability of remote sensing data, DL-based image semantic segmentation has attracted growing interest in the remote sensing community. The ideal scenario of DL application requires a vast number of annotation data [...] Read more.
Inspired by the tremendous success of deep learning (DL) and the increased availability of remote sensing data, DL-based image semantic segmentation has attracted growing interest in the remote sensing community. The ideal scenario of DL application requires a vast number of annotation data with the same feature distribution as the area of interest. However, obtaining such enormous training sets that suit the data distribution of the target area is highly time-consuming and costly. Consistency-regularization-based semi-supervised learning (SSL) methods have gained growing popularity thanks to their ease of implementation and remarkable performance. However, there have been limited applications of SSL in remote sensing. This study comprehensively analyzed several advanced SSL methods based on consistency regularization from the perspective of data- and model-level perturbation. Then, an end-to-end SSL approach based on a hybrid perturbation paradigm was introduced to improve the DL model’s performance with a limited number of labels. The proposed method integrates the semantic boundary information to generate more meaningful mixing images when performing data-level perturbation. Additionally, by using implicit pseudo-supervision based on model-level perturbation, it eliminates the need to set extra threshold parameters in training. Furthermore, it can be flexibly paired with the DL model in an end-to-end manner, as opposed to the separated training stages used in the traditional pseudo-labeling. Experimental results for five remote sensing benchmark datasets in the application of segmentation of roads, buildings, and land cover demonstrated the effectiveness and robustness of the proposed approach. It is particularly encouraging that the ratio of accuracy obtained using the proposed method with 5% labels to that using the purely supervised method with 100% labels was more than 89% on all benchmark datasets. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

22 pages, 10622 KiB  
Article
Multiple Instance Learning Convolutional Neural Networks for Fine-Grained Aircraft Recognition
by Xiaolan Huang, Kai Xu, Chuming Huang, Chengrui Wang and Kun Qin
Remote Sens. 2021, 13(24), 5132; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13245132 - 17 Dec 2021
Cited by 5 | Viewed by 2549
Abstract
The key to fine-grained aircraft recognition is discovering the subtle traits that can distinguish different subcategories. Early approaches leverage part annotations of fine-grained objects to derive rich representations. However, manual labeling part information is cumbersome. In response to this issue, previous CNN-based methods [...] Read more.
The key to fine-grained aircraft recognition is discovering the subtle traits that can distinguish different subcategories. Early approaches leverage part annotations of fine-grained objects to derive rich representations. However, manual labeling part information is cumbersome. In response to this issue, previous CNN-based methods reuse the backbone network to extract part-discrimination features, the inference process of which consumes much time. Therefore, we introduce generalized multiple instance learning (MIL) into fine-grained recognition. In generalized MIL, an aircraft is assumed to consist of multiple instances (such as head, tail, and body). Firstly, instance-level representations are obtained by the feature extractor and instance conversion component. Secondly, the obtained instance features are scored by an MIL classifier, which can yield high-level part semantics. Finally, a fine-grained object label is inferred by a MIL pooling function that aggregates multiple instance scores. The proposed approach is trained end-to-end without part annotations and complex location networks. Experimental evidence is conducted to prove the feasibility and effectiveness of our approach on combined aircraft images (CAIs). Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

26 pages, 4788 KiB  
Article
SDFCNv2: An Improved FCN Framework for Remote Sensing Images Semantic Segmentation
by Guanzhou Chen, Xiaoliang Tan, Beibei Guo, Kun Zhu, Puyun Liao, Tong Wang, Qing Wang and Xiaodong Zhang
Remote Sens. 2021, 13(23), 4902; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13234902 - 03 Dec 2021
Cited by 27 | Viewed by 3379
Abstract
Semantic segmentation is a fundamental task in remote sensing image analysis (RSIA). Fully convolutional networks (FCNs) have achieved state-of-the-art performance in the task of semantic segmentation of natural scene images. However, due to distinctive differences between natural scene images and remotely-sensed (RS) images, [...] Read more.
Semantic segmentation is a fundamental task in remote sensing image analysis (RSIA). Fully convolutional networks (FCNs) have achieved state-of-the-art performance in the task of semantic segmentation of natural scene images. However, due to distinctive differences between natural scene images and remotely-sensed (RS) images, FCN-based semantic segmentation methods from the field of computer vision cannot achieve promising performances on RS images without modifications. In previous work, we proposed an RS image semantic segmentation framework SDFCNv1, combined with a majority voting postprocessing method. Nevertheless, it still has some drawbacks, such as small receptive field and large number of parameters. In this paper, we propose an improved semantic segmentation framework SDFCNv2 based on SDFCNv1, to conduct optimal semantic segmentation on RS images. We first construct a novel FCN model with hybrid basic convolutional (HBC) blocks and spatial-channel-fusion squeeze-and-excitation (SCFSE) modules, which occupies a larger receptive field and fewer network model parameters. We also put forward a data augmentation method based on spectral-specific stochastic-gamma-transform-based (SSSGT-based) during the model training process to improve generalizability of our model. Besides, we design a mask-weighted voting decision fusion postprocessing algorithm for image segmentation on overlarge RS images. We conducted several comparative experiments on two public datasets and a real surveying and mapping dataset. Extensive experimental results demonstrate that compared with the SDFCNv1 framework, our SDFCNv2 framework can increase the mIoU metric by up to 5.22% while only using about half of parameters. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

20 pages, 2985 KiB  
Article
Harbor Aquaculture Area Extraction Aided with an Integration-Enhanced Gradient Descent Algorithm
by Yafeng Zhong, Siyuan Liao, Guo Yu, Dongyang Fu and Haoen Huang
Remote Sens. 2021, 13(22), 4554; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13224554 - 12 Nov 2021
Cited by 5 | Viewed by 1605
Abstract
In this study, the harbor aquaculture area tested is Zhanjiang coast, and for the remote sensing data, we use images from the GaoFen-1 satellite. In order to achieve a superior extraction performance, we propose the use of an integration-enhanced gradient descent (IEGD) algorithm. [...] Read more.
In this study, the harbor aquaculture area tested is Zhanjiang coast, and for the remote sensing data, we use images from the GaoFen-1 satellite. In order to achieve a superior extraction performance, we propose the use of an integration-enhanced gradient descent (IEGD) algorithm. The key idea of this algorithm is to add an integration gradient term on the basis of the gradient descent (GD) algorithm to obtain high-precision extraction of the harbor aquaculture area. To evaluate the extraction performance of the proposed IEGD algorithm, comparative experiments were performed using three supervised classification methods: the neural network method, the support vector machine method, and the maximum likelihood method. From the results extracted, we found that the overall accuracy and F-score of the proposed IEGD algorithm for the overall performance were 0.9538 and 0.9541, meaning that the IEGD algorithm outperformed the three comparison algorithms. Both the visualized and quantitative results demonstrate the high precision of the proposed IEGD algorithm aided with the CEM scheme for the harbor aquaculture area extraction. These results confirm the effectiveness and practicality of the proposed IEGD algorithm in harbor aquaculture area extraction from GF-1 satellite data. Added to that, the proposed IEGD algorithm can improve the extraction accuracy of large-scale images and be employed for the extraction of various aquaculture areas. Given that the IEGD algorithm is a type of supervised classification algorithm, it relies heavily on the spectral feature information of the aquaculture object. For this reason, if the spectral feature information of the region of interest is not selected properly, the extraction performance of the overall aquaculture area will be extremely reduced. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

24 pages, 4441 KiB  
Article
TRS: Transformers for Remote Sensing Scene Classification
by Jianrong Zhang, Hongwei Zhao and Jiao Li
Remote Sens. 2021, 13(20), 4143; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13204143 - 16 Oct 2021
Cited by 69 | Viewed by 4469
Abstract
Remote sensing scene classification remains challenging due to the complexity and variety of scenes. With the development of attention-based methods, Convolutional Neural Networks (CNNs) have achieved competitive performance in remote sensing scene classification tasks. As an important method of the attention-based model, the [...] Read more.
Remote sensing scene classification remains challenging due to the complexity and variety of scenes. With the development of attention-based methods, Convolutional Neural Networks (CNNs) have achieved competitive performance in remote sensing scene classification tasks. As an important method of the attention-based model, the Transformer has achieved great success in the field of natural language processing. Recently, the Transformer has been used for computer vision tasks. However, most existing methods divide the original image into multiple patches and encode the patches as the input of the Transformer, which limits the model’s ability to learn the overall features of the image. In this paper, we propose a new remote sensing scene classification method, Remote Sensing Transformer (TRS), a powerful “pure CNNs → Convolution + Transformer → pure Transformers” structure. First, we integrate self-attention into ResNet in a novel way, using our proposed Multi-Head Self-Attention layer instead of 3 × 3 spatial revolutions in the bottleneck. Then we connect multiple pure Transformer encoders to further improve the representation learning performance completely depending on attention. Finally, we use a linear classifier for classification. We train our model on four public remote sensing scene datasets: UC-Merced, AID, NWPU-RESISC45, and OPTIMAL-31. The experimental results show that TRS exceeds the state-of-the-art methods and achieves higher accuracy. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

19 pages, 3791 KiB  
Article
Spatial-Aware Network for Hyperspectral Image Classification
by Yantao Wei and Yicong Zhou
Remote Sens. 2021, 13(16), 3232; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163232 - 14 Aug 2021
Cited by 8 | Viewed by 2640
Abstract
Deep learning is now receiving widespread attention in hyperspectral image (HSI) classification. However, due to the imbalance between a huge number of weights and limited training samples, many problems and difficulties have arisen from the use of deep learning methods in HSI classification. [...] Read more.
Deep learning is now receiving widespread attention in hyperspectral image (HSI) classification. However, due to the imbalance between a huge number of weights and limited training samples, many problems and difficulties have arisen from the use of deep learning methods in HSI classification. To handle this issue, an efficient deep learning-based HSI classification method, namely, spatial-aware network (SANet) has been proposed in this paper. The main idea of SANet is to exploit discriminative spectral-spatial features by incorporating prior domain knowledge into the deep architecture, where edge-preserving side window filters are used as the convolution kernels. Thus, SANet has a small number of parameters to optimize. This makes it fit for small sample sizes. Furthermore, SANet is able not only to aware local spatial structures using side window filtering framework, but also to learn discriminative features making use of the hierarchical architecture and limited label information. The experimental results on four widely used HSI data sets demonstrate that our proposed SANet significantly outperforms many state-of-the-art approaches when only a small number of training samples are available. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

20 pages, 7154 KiB  
Article
Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images
by Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang and Xiaoliang Meng
Remote Sens. 2021, 13(16), 3065; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163065 - 04 Aug 2021
Cited by 77 | Viewed by 7504
Abstract
Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and [...] Read more.
Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

17 pages, 2758 KiB  
Article
3D Imaging Algorithm of Directional Borehole Radar Based on Root-MUSIC
by Wentian Wang, Sixin Liu, Xuzhang Shen and Wenjun Zheng
Remote Sens. 2021, 13(15), 2957; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13152957 - 27 Jul 2021
Cited by 5 | Viewed by 1818
Abstract
A directional borehole radar consists of one transmitting antenna in the borehole and four receiving antennas distributed at equal angles in a ring. The receiving antennas can determine the depth and orientation of targets beside the borehole. However, the problem of target orientation [...] Read more.
A directional borehole radar consists of one transmitting antenna in the borehole and four receiving antennas distributed at equal angles in a ring. The receiving antennas can determine the depth and orientation of targets beside the borehole. However, the problem of target orientation determination and 3D imaging algorithms remains a technological challenge. The MUSIC (multiple signal classification) algorithm requires a peak search, so the accuracy of the operation is limited by the angle interval. Based on the MUSIC algorithm, the Root-MUSIC algorithm is proposed and implemented. By replacing the spectral peak search with calculating the roots of the polynomials greatly improves the orientation recognition accuracy. Finally, the results obtained using the above algorithm are verified with synthetic data and compared with the results of the MUSIC algorithm. The results show that both the MUSIC algorithm and the Root-MUSIC algorithm can achieve very good orientation determination and 3D imaging results. In terms of accuracy, the Root-MUSIC algorithm has an obvious improvement compared with the MUSIC algorithm. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Figure 1

21 pages, 9785 KiB  
Article
Sentinel-2 Remote Sensed Image Classification with Patchwise Trained ConvNets for Grassland Habitat Discrimination
by Paolo Fazzini, Giuseppina De Felice Proia, Maria Adamo, Palma Blonda, Francesco Petracchini, Luigi Forte and Cristina Tarantino
Remote Sens. 2021, 13(12), 2276; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13122276 - 10 Jun 2021
Cited by 7 | Viewed by 2772
Abstract
The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the “Murgia Alta” protected site. To this end, we compared two approaches differing only by [...] Read more.
The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the “Murgia Alta” protected site. To this end, we compared two approaches differing only by the first layer machinery, which, in one case, is instantiated as a fully-connected layer and, in the other case, results in a ConvNet equipped with kernels covering the whole input (wide-kernel ConvNet). A patchwise approach, tessellating training reference data in square patches, was adopted. Besides assessing the effectiveness of ConvNets with patched multispectral data, we analyzed how the information needed for classification spreads to patterns over convex sets of pixels. Our results show that: (a) with an F1-score of around 97% (5 × 5 patch size), ConvNets provides an excellent tool for patch-based pattern recognition with multispectral input data without requiring special feature extraction; (b) the information spreads over the limit of a single pixel: the performance of the network increases until 5 × 5 patch sizes are used and then ConvNet performance starts decreasing. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

24 pages, 12000 KiB  
Article
Spectral and Spatial Global Context Attention for Hyperspectral Image Classification
by Zhongwei Li, Xingshuai Cui, Leiquan Wang, Hao Zhang, Xue Zhu and Yajing Zhang
Remote Sens. 2021, 13(4), 771; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13040771 - 19 Feb 2021
Cited by 23 | Viewed by 2765
Abstract
Recently, hyperspectral image (HSI) classification has attracted increasing attention in the remote sensing field. Plenty of CNN-based methods with diverse attention mechanisms (AMs) have been proposed for HSI classification due to AMs being able to improve the quality of feature representations. However, some [...] Read more.
Recently, hyperspectral image (HSI) classification has attracted increasing attention in the remote sensing field. Plenty of CNN-based methods with diverse attention mechanisms (AMs) have been proposed for HSI classification due to AMs being able to improve the quality of feature representations. However, some of the previous AMs squeeze global spatial or channel information directly by pooling operations to yield feature descriptors, which inadequately utilize global contextual information. Besides, some AMs cannot exploit the interactions among channels or positions with the aid of nonlinear transformation well. In this article, a spectral-spatial network with channel and position global context (GC) attention (SSGCA) is proposed to capture discriminative spectral and spatial features. Firstly, a spectral-spatial network is designed to extract spectral and spatial features. Secondly, two novel GC attentions are proposed to optimize the spectral and spatial features respectively for feature enhancement. The channel GC attention is used to capture channel dependencies to emphasize informative features while the position GC attention focuses on position dependencies. Both GC attentions aggregate global contextual features of positions or channels adequately, following a nonlinear transformation. Experimental results on several public HSI datasets demonstrate that the spectral-spatial network with GC attentions outperforms other related methods. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

23 pages, 11524 KiB  
Article
Hyperspectral Image Spectral–Spatial Classification Method Based on Deep Adaptive Feature Fusion
by Caihong Mu, Yijin Liu and Yi Liu
Remote Sens. 2021, 13(4), 746; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13040746 - 18 Feb 2021
Cited by 11 | Viewed by 2586
Abstract
Convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds [...] Read more.
Convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. Many algorithms focus on the deep extraction of a single kind of feature to improve classification. There have been few studies on the deep extraction of two or more kinds of fusion features and the combination of spatial and spectral features for classification. The authors of this paper propose an HSI spectral–spatial classification method based on deep adaptive feature fusion (SSDF). This method first implements the deep adaptive fusion of two hyperspectral features, and then it performs spectral–spatial classification on the fused features. In SSDF, a U-shaped deep network model with the principal component features as the model input and the edge features as the model label is designed to adaptively fuse two kinds of different features. One comprises the edge features of the HSIs extracted by the guided filter, and the other comprises the principal component features obtained by dimensionality reduction of HSIs using principal component analysis. The fused new features are input into a multi-scale and multi-level feature extraction model for further extraction of deep features, which are then combined with the spectral features extracted by the long short-term memory (LSTM) model for classification. The experimental results on three datasets demonstrated that the performance of the proposed SSDF was superior to several state-of-the-art methods. Additionally, SSDF was found to be able to perform best as the number of training samples decreased sharply, and it could also obtain a high classification accuracy for categories with few samples. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

26 pages, 13189 KiB  
Article
High-Resolution SAR Image Classification Using Multi-Scale Deep Feature Fusion and Covariance Pooling Manifold Network
by Wenkai Liang, Yan Wu, Ming Li, Yice Cao and Xin Hu
Remote Sens. 2021, 13(2), 328; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13020328 - 19 Jan 2021
Cited by 13 | Viewed by 3808
Abstract
The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case [...] Read more.
The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

34 pages, 55823 KiB  
Article
Attention-Based Pyramid Network for Segmentation and Classification of High-Resolution and Hyperspectral Remote Sensing Images
by Qingsong Xu, Xin Yuan, Chaojun Ouyang and Yue Zeng
Remote Sens. 2020, 12(21), 3501; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12213501 - 24 Oct 2020
Cited by 14 | Viewed by 3505
Abstract
Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop [...] Read more.
Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: (i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; (ii) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and (iii) cross-scale attention in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial-spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial-spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

18 pages, 4851 KiB  
Article
An Effective Lunar Crater Recognition Algorithm Based on Convolutional Neural Network
by Song Wang, Zizhu Fan, Zhengming Li, Hong Zhang and Chao Wei
Remote Sens. 2020, 12(17), 2694; https://0-doi-org.brum.beds.ac.uk/10.3390/rs12172694 - 20 Aug 2020
Cited by 21 | Viewed by 4090
Abstract
The lunar crater recognition plays a key role in lunar exploration. Traditional crater recognition methods are mainly based on the human observation that is usually combined with classical machine learning methods. These methods have some drawbacks, such as lacking the objective criterion. Moreover, [...] Read more.
The lunar crater recognition plays a key role in lunar exploration. Traditional crater recognition methods are mainly based on the human observation that is usually combined with classical machine learning methods. These methods have some drawbacks, such as lacking the objective criterion. Moreover, they can hardly achieve desirable recognition results in small or overlapping craters. To address these problems, we propose a new convolutional neural network termed effective residual U-Net (ERU-Net) to recognize craters from lunar digital elevation model (DEM) images. ERU-Net first detects crater edges in lunar DEM data. Then, it uses template matching to compute the position and size of craters. ERU-Net is based on U-Net and uses the residual convolution block instead of the traditional convolution, which combines the advantages of U-Net and residual network. In ERU-Net, the size of the input image is the same as that of the output image. Since our network uses residual units, the training process of ERU-Net is simple, and the proposed model can be easily optimized. ERU-Net gets better recognition results when its network structure is deepened. The method targets at the rim of the crater, and it can recognize overlap craters. In theory, our proposed network can recognize all kinds of impact craters. In the lunar crater recognition, our model achieves high recall (83.59%) and precision (84.80%) on DEM. The recall of our method is higher than those of other deep learning methods. The experiment results show that it is feasible to exploit our network to recognize craters from the lunar DEM. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

Review

Jump to: Research

51 pages, 51599 KiB  
Review
Review of Image Classification Algorithms Based on Convolutional Neural Networks
by Leiyu Chen, Shaobo Li, Qiang Bai, Jing Yang, Sanlong Jiang and Yanming Miao
Remote Sens. 2021, 13(22), 4712; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13224712 - 21 Nov 2021
Cited by 162 | Viewed by 39858
Abstract
Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN [...] Read more.
Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. In the wake of these successes, CNN-based methods have emerged in remote sensing image scene classification and achieved advanced classification accuracy. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures. Along the way, we analyze (1) the basic structure of artificial neural networks (ANNs) and the basic network layers of CNNs, (2) the classic predecessor network models, (3) the recent SOAT network algorithms, (4) comprehensive comparison of various image classification methods mentioned in this article. Finally, we have also summarized the main analysis and discussion in this article, as well as introduce some of the current trends. Full article
(This article belongs to the Special Issue Deep Learning for Remote Sensing Image Classification)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-18
Back to TopTop