Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Browser

► Journal Browser

Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Remote Sensing (ISSN 2072-4292).

Deadline for manuscript submissions: closed (31 March 2021) | Viewed by 83010

Share This Special Issue

Special Issue Editors

Prof. Dr. Guoqing Li

E-Mail Website
Guest Editor

Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
Interests: high-performance geo-computation; big earth data; data science
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Bing Zhang

E-Mail Website
Guest Editor

Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
Interests: hyperspectral remote sensing; dynamic monitoring of global resource environment with remote sensing; intelligent interpretation of remotely sensed big data
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Thomas Blaschke

E-Mail Website
Guest Editor

Interfaculty Department of Geoinformatics - Z GIS, University of Salzburg, A-5020 Salzburg, Austria
Interests: GIS; remote sensing; spatial analysis and GIS-based spatial decision support systems; object-based image processing
Special Issues, Collections and Topics in MDPI journals

Dr. Junshi Xia

E-Mail Website
Guest Editor

Geoinformatics Unit, RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan
Interests: high-performance geo-computation; big earth data; data science
Special Issues, Collections and Topics in MDPI journals

Prof. Chuang Liu

E-Mail Website
Guest Editor

Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
Interests: global change data; information and its application in integrated physical geography

Prof. Carol Song

E-Mail Website
Guest Editor

Rosen Center for Advanced Computing (RCAC), Purdue University, West Lafayette, IN 47907, USA
Interests: high-performance and distributed computing; data infrastructure; cyberinfrastructure; science gateways

Prof. Dr. Philippe De Maeyer

E-Mail Website
Guest Editor

Department of Geography, Ghent University, 9000 Gent, Belgium
Interests: GIS; remote sensing; land cover/use; risk modeling

Prof. Dr. Yifang Ban

E-Mail Website
Guest Editor

Division of Geoinformatics and Department of Urban Planning and Environment at KTH Royal Institute of Technology in Stockholm, Stockholm, Sweden
Interests: EO big data analytics; multitemporal remote sensing; SAR-based classification and change detection; urban mapping and wildfire monitoring
Special Issues, Collections and Topics in MDPI journals

Dr. Xiaochuang Yao

E-Mail Website
Guest Editor

College of Land Science and Technology, China Agricultural University, Beijing 100083, China
Interests: spatial big data; data management and analysis; GIS; remote sensing
Special Issues, Collections and Topics in MDPI journals

Dr. Amani J. Uisso

E-Mail Website
Guest Editor

Tanzania Forestry Research Institute (TAFORI), Tanzania
Interests: land use planning; land suitability analysis; social forestry; natural resources management

Special Issue Information

Dear Colleagues,

In the last few years, remote sensing has entered the era of big data characterized by “volume, velocity, variety, and value”. Deep learning has proven to be efficient for large remote sensing data sets, particularly for feature or target detection, and for image and data classification. Deep learning-based applications are also emerging in various domains, such as disaster assessment, agricultural monitoring, and urban planning. Still, strategies for the creation of massive sample datasets and for the construction of deep learning networks play essential roles in the success of deep learning. Researchers have developed a number of marker sample datasets for object detection and image classification, which have supported successful applications of deep learning in remote sensing. Hence, the joint publication and release of these sample databases and related algorithms or applications will undoubtedly promote the further development of deep learning in the field of remote sensing and will increase transparency, transferability, and reproducibility.

This Joint Special Issue calls for original outcomes from research activities and aims to publish simultaneously remote sensing sample datasets and the description of related algorithms or applications from the same research team or scholars. Our aim is for the jointly published papers to promote a transparent use of deep learning in remote sensing, as well as sharing of high-precision sample datasets while simultaneously documented through the corresponding papers of the joint Special Issue.

The outcomes of a research activity are not only a discovery paper, but a relevant research data and data paper. Supported by National Earth Observation Data Center (NODA), we invite original results of a research activity for a joint Special Issue of three publishers, including Global Change Research Data Publishing & Repository (DOI:10.3974, Regular member of the World Data System) for publishing datasets and two journals, Global Change Research Data & Discovery (ISSN 2096-3645) for publishing data papers and Remote Sensing (ISSN 2072-4292) for publishing discovery papers based on the relevant datasets and data papers. All of the datasets, data papers, and discovery papers are peer-reviewed and openly accessible.

The deadline for dataset and data paper submissions to Global Change Research Data Publishing & Repository and the Journal of Global Change Data & Discovery (http://www.geodoi.ac.cn/WebEn/IssuesInfo.aspx?ID=202001) is 31 June 2020.

Potential topics include but are not limited to:

Remote sensing data sample datasets and descriptions for deep learning (e.g., datasets on land cover, disasters, agriculture, buildings, transportation infrastructure, ships);
Innovative deep learning algorithms for remote sensing data processing (e.g., object or target detection, classification, parameter adaptation);
Training and testing deep learning algorithms and solutions to remote sensing problems;
Deep learning for image processing and classification;
Deep learning for image understanding including semantic labeling, object detection, or image retrieval;
Deep learning for remote sensing data fusion;
Deep learning with scarce or low-quality remote sensing data across resolutions or sensors;
Deep learning for time-series applications;
Applications of deep learning in remote sensing (e.g., disaster assessment, agricultural monitoring, urban planning).

Prof. Guoqing Li
Prof. Bing Zhang
Prof. Dr. Thomas Blaschke
Dr. Junshi Xia
Prof. Chuang Liu
Prof. Carol Song
Prof. Philippe De Maeyer
Prof. Yifang Ban
Dr. Xiaochuang Yao
Dr. Amani J. Uisso

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

Remote sensing
Deep learning
Sample datasets
Big data analysis
Image processing algorithms
Remote sensing applications

Published Papers (14 papers)

Download All Papers

Research

Jump to: Review, Other

25 pages, 35502 KiB

Open AccessArticle

YOLO for Penguin Detection and Counting Based on Remote Sensing Images

by Jiahui Wu, Wen Xu, Jianfeng He and Musheng Lan

Remote Sens. 2023, 15(10), 2598; https://doi.org/10.3390/rs15102598 - 16 May 2023

Cited by 4 | Viewed by 2356

Abstract

As the largest species of birds in Antarctica, penguins are called “biological indicators”. Changes in the environment will cause population fluctuations. Therefore, developing a penguin census regularly will not only help carry out conservation activities but also provides a basis for studying climate change. Traditionally, scholars often use indirect methods, e.g., identifying penguin guano and establishing regression relationships to estimate the size of penguin colonies. In this paper, we explore the feasibility of automatic object detection algorithms based on aerial images, which locate each penguin directly. We build a dataset consisting of images taken at 400 m altitude over the island populated by Adelie penguins, which are cropped with a resolution of 640 × 640. To address the challenges of detecting minuscule penguins (often 10 pixels extent) amidst complex backgrounds in our dataset, we propose a new object detection network, named YoloPd (Yolo for penguin detection). Specifically, a multiple frequency features fusion module and a Bottleneck aggregation layer are proposed to strengthen feature representations for smaller penguins. Furthermore, the Transformer aggregation layer and efficient attention module are designed to capture global features with the aim of filtering out background interference. With respect to the latency/accuracy trade-off, YoloPd surpasses the classical detector Faster R-CNN by 8.5% in mean precision (mAP). It also beats the latest detector Yolov7 by 2.3% in F1 score with fewer parameters. Under YoloPd, the average counting accuracy reaches 94.6%, which is quite promising. The results demonstrate the potential of automatic detectors and provide a new direction for penguin counting. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

18 pages, 31448 KiB

Open AccessArticle

An Improved Faster R-CNN Method to Detect Tailings Ponds from High-Resolution Remote Sensing Images

by Dongchuan Yan, Guoqing Li, Xiangqiang Li, Hao Zhang, Hua Lei, Kaixuan Lu, Minghua Cheng and Fuxiao Zhu

Remote Sens. 2021, 13(11), 2052; https://doi.org/10.3390/rs13112052 - 23 May 2021

Cited by 21 | Viewed by 2894

Abstract

Dam failure of tailings ponds can result in serious casualties and environmental pollution. Therefore, timely and accurate monitoring is crucial for managing tailings ponds and preventing damage from tailings pond accidents. Remote sensing technology facilitates the regular extraction and monitoring of tailings pond information. However, traditional remote sensing techniques are inefficient and have low levels of automation, which hinders the large-scale, high-frequency, and high-precision extraction of tailings pond information. Moreover, research into the automatic and intelligent extraction of tailings pond information from high-resolution remote sensing images is relatively rare. However, the deep learning end-to-end model offers a solution to this problem. This study proposes an intelligent and high-precision method for extracting tailings pond information from high-resolution images, which improves deep learning target detection model: faster region-based convolutional neural network (Faster R-CNN). A comparison study is conducted and the model input size with the highest precision is selected. The feature pyramid network (FPN) is adopted to obtain multiscale feature maps with rich context information, the attention mechanism is used to improve the FPN, and the contribution degrees of feature channels are recalibrated. The model test results based on GoogleEarth high-resolution remote sensing images indicate a significant increase in the average precision (AP) and recall of tailings pond detection from that of Faster R-CNN by 5.6% and 10.9%, reaching 85.7% and 62.9%, respectively. Considering the current rapid increase in high-resolution remote sensing images, this method will be important for large-scale, high-precision, and intelligent monitoring of tailings ponds, which will greatly improve the decision-making efficiency in tailings pond management. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Figure 1

20 pages, 9798 KiB

Open AccessArticle

Land Cover Mapping and Ecological Risk Assessment in the Context of Recent Ecological Migration

by Tingting Zhang, Zhenrong Du, Jianyu Yang, Xiaochuang Yao, Cong Ou, Bowen Niu and Shuai Yan

Remote Sens. 2021, 13(7), 1381; https://doi.org/10.3390/rs13071381 - 03 Apr 2021

Cited by 18 | Viewed by 2929

Abstract

In order to protect the ecological environment and solve the poverty problem in the western region, China has established an ecological migration (EM) policy. This policy aims to relocate populations from poverty-stricken areas with fragile ecological environments, which inevitably leads to changes in land cover and the ecological environment. The objective of this study was to identify the effects of EM in a typical region (Wuwei), including changes in the land cover and ecological risk (ER). A land cover change monitoring method was implemented for the 2010–2019 period for six land cover classes using random forest, which is an effective supervised machine learning method. The land cover change patterns were analyzed by determining the area changes of the six classes and applying a land use transition matrix, and a landscape ecological risk model based on landscape disturbance and fragility was used. Our results demonstrate that the increase and decrease in the area of cultivated land, unused land, and construction land can be divided into two stages (2010–2015 and 2015–2019). The area of water and perennial snow doubled during the study periods. The major land cover transitions were between unused land and construction land and between unused land and crop land. In addition, the ER value for the Qilian Mountain National Nature Reserve decreased because of the implementation of EM in the study area, indicating that the ecological environment was effectively improved. The results demonstrate the advantage of the proposed approach in understanding the impact of EM on regional land cover changes and the ecological environment so as to provide guidance for follow-up planning and development. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

21 pages, 66554 KiB

Open AccessArticle

Semi-/Weakly-Supervised Semantic Segmentation Method and Its Application for Coastal Aquaculture Areas Based on Multi-Source Remote Sensing Images—Taking the Fujian Coastal Area (Mainly Sanduo) as an Example

by Chenbin Liang, Bo Cheng, Baihua Xiao, Chenlinqiu He, Xunan Liu, Ning Jia and Jinfen Chen

Remote Sens. 2021, 13(6), 1083; https://doi.org/10.3390/rs13061083 - 12 Mar 2021

Cited by 17 | Viewed by 2947

Abstract

Coastal aquaculture areas are some of the main areas to obtain marine fishery resources and are vulnerable to storm-tide disasters. Obtaining the information of coastal aquaculture areas quickly and accurately is important for the scientific management and planning of aquaculture resources. Recently, deep neural networks have been widely used in remote sensing to deal with many problems, such as scene classification and object detection, and there are many data sources with different spatial resolutions and different uses with the development of remote sensing technology. Thus, using deep learning networks to extract coastal aquaculture areas often encounters the following problems: (1) the difficulty in labeling; (2) the poor robustness of the model; (3) the spatial resolution of the image to be processed is inconsistent with that of the existing samples. In order to fix these problems, this paper proposes a novel semi-/weakly-supervised method, the semi-/weakly-supervised semantic segmentation network (Semi-SSN), and adopts 3 data sources: GaoFen-2 image, GaoFen-1(PMS)image, and GanFen-1(WFV)image with a 0.8 m, 2 m, and 16 m spatial resolution, respectively, and through experiments, we analyze the extraction effect of the model comprehensively. After comparing with other the-state-of-art methods and verifying on an open remote sensing dataset, we take the Fujian coastal area (mainly Sanduo) as the experimental area and employ our method to detect the effect of storm-tide disasters on coastal aquaculture areas, monitor the production, and make the distribution map of coastal aquaculture areas. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

22 pages, 20753 KiB

Open AccessArticle

Building Damage Detection Using U-Net with Attention Mechanism from Pre- and Post-Disaster Remote Sensing Datasets

by Chuyi Wu, Feng Zhang, Junshi Xia, Yichen Xu, Guoqing Li, Jibo Xie, Zhenhong Du and Renyi Liu

Remote Sens. 2021, 13(5), 905; https://doi.org/10.3390/rs13050905 - 28 Feb 2021

Cited by 53 | Viewed by 5953

Abstract

The building damage status is vital to plan rescue and reconstruction after a disaster and is also hard to detect and judge its level. Most existing studies focus on binary classification, and the attention of the model is distracted. In this study, we proposed a Siamese neural network that can localize and classify damaged buildings at one time. The main parts of this network are a variety of attention U-Nets using different backbones. The attention mechanism enables the network to pay more attention to the effective features and channels, so as to reduce the impact of useless features. We train them using the xBD dataset, which is a large-scale dataset for the advancement of building damage assessment, and compare their result balanced F (F1) scores. The score demonstrates that the performance of SEresNeXt with an attention mechanism gives the best performance among single models, with the F1 score reaching 0.787. To improve the accuracy, we fused the results and got the best overall F1 score of 0.792. To verify the transferability and robustness of the model, we selected the dataset on the Maxar Open Data Program of two recent disasters to investigate the performance. By visual comparison, the results show that our model is robust and transferable. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

19 pages, 30340 KiB

Open AccessArticle

Identification of Abandoned Jujube Fields Using Multi-Temporal High-Resolution Imagery and Machine Learning

by Xingrong Li, Chenghai Yang, Hongri Zhang, Panpan Wang, Jia Tang, Yanqin Tian and Qing Zhang

Remote Sens. 2021, 13(4), 801; https://doi.org/10.3390/rs13040801 - 22 Feb 2021

Cited by 9 | Viewed by 2389

Abstract

The jujube industry plays a very important role in the agricultural industrial structure of Xinjiang, China. In recent years, the abandonment of jujube fields has gradually emerged. It is critical to inventory the abandoned land soon after it is generated to adjust agricultural production better and prevent the negative impacts from the abandonment (such as outbreaks of diseases, insect pests, and fires). High-resolution multi-temporal satellite remote sensing images can be used to identify subtle differences among crops and provide a good tool for solving this problem. In this research, both field-based and pixel-based classification approaches using field boundaries were used to estimate the percentage of abandoned jujube fields with multi-temporal high spatial resolution satellite images (Gaofen-1 and Gaofen-6) and the Random Forest algorithm. The results showed that both approaches produced good classification results and similar distributions of abandoned fields. The overall accuracy was 91.1% for the field-based classification and 90.0% for the pixel-based classification, and the Kappa was 0.866 and 0.848 for the respective classifications. The areas of abandoned land detected in the field-based and pixel-based classification maps were 806.09 ha and 828.21 ha, respectively, accounting for 8.97% and 9.11% of the study area. In addition, feature importance evaluations of the two approaches showed that the overall importance of texture features was higher than that of vegetation indices and that 31 October and 10 November were important dates for abandoned land detection. The methodology proposed in this study will be useful for identifying abandoned jujube fields and have the potential for large-scale application. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

12 pages, 19293 KiB

Open AccessCommunication

A Public Dataset for Fine-Grained Ship Classification in Optical Remote Sensing Images

by Yanghua Di, Zhiguo Jiang and Haopeng Zhang

Remote Sens. 2021, 13(4), 747; https://doi.org/10.3390/rs13040747 - 18 Feb 2021

Cited by 36 | Viewed by 5966

Abstract

Fine-grained visual categorization (FGVC) is an important and challenging problem due to large intra-class differences and small inter-class differences caused by deformation, illumination, angles, etc. Although major advances have been achieved in natural images in the past few years due to the release of popular datasets such as the CUB-200-2011, Stanford Cars and Aircraft datasets, fine-grained ship classification in remote sensing images has been rarely studied because of relative scarcity of publicly available datasets. In this paper, we investigate a large amount of remote sensing image data of sea ships and determine most common 42 categories for fine-grained visual categorization. Based our previous DSCR dataset, a dataset for ship classification in remote sensing images, we collect more remote sensing images containing warships and civilian ships of various scales from Google Earth and other popular remote sensing image datasets including DOTA, HRSC2016, NWPU VHR-10, We call our dataset FGSCR-42, meaning a dataset for Fine-Grained Ship Classification in Remote sensing images with 42 categories. The whole dataset of FGSCR-42 contains 9320 images of most common types of ships. We evaluate popular object classification algorithms and fine-grained visual categorization algorithms to build a benchmark. Our FGSCR-42 dataset is publicly available at our webpages. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

19 pages, 5528 KiB

Open AccessArticle

SDGH-Net: Ship Detection in Optical Remote Sensing Images Based on Gaussian Heatmap Regression

by Zhenqing Wang, Yi Zhou, Futao Wang, Shixin Wang and Zhiyu Xu

Remote Sens. 2021, 13(3), 499; https://doi.org/10.3390/rs13030499 - 30 Jan 2021

Cited by 34 | Viewed by 8484

Abstract

The ship detection task using optical remote sensing images is important for in maritime safety, port management and ship rescue. With the wide application of deep learning to remote sensing, a series of target detection algorithms, such as faster regions with convolution neural network feature (R-CNN) and You Only Look Once (YOLO), have been developed to detect ships in remote sensing images. These detection algorithms use fully connected layer direct regression to obtain coordinate points. Although training and forward speed are fast, they lack spatial generalization ability. To avoid the over-fitting problem that may arise from the fully connected layer, we propose a fully convolutional neural network, SDGH-Net, based on Gaussian heatmap regression. SDGH-Net uses an encoder–decoder structure to obtain the ship area feature map by direct regression. After simple post-processing, the ship polygon annotation can be obtained without non-maximum suppression (NMS) processing. To speed up model training, we added a batch normalization (BN) processing layer. To increase the receptive field while controlling the number of learning parameters, we introduced dilated convolution and added it at different rates to fuse the features of different scales. We tested the performance of our proposed method using a public ship dataset HRSC2016. The experimental results show that this method improves the recall rate of ships, and the F-measure is 85.05%, which surpasses all other methods we used for comparison. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

27 pages, 6557 KiB

Open AccessArticle

Deep Learning for Land Cover Change Detection

by Oliver Sefrin, Felix M. Riese and Sina Keller

Remote Sens. 2021, 13(1), 78; https://doi.org/10.3390/rs13010078 - 28 Dec 2020

Cited by 71 | Viewed by 12330

Abstract

Land cover and its change are crucial for many environmental applications. This study focuses on the land cover classification and change detection with multitemporal and multispectral Sentinel-2 satellite data. To address the challenging land cover change detection task, we rely on two different deep learning architectures and selected pre-processing steps. For example, we define an excluded class and deal with temporal water shoreline changes in the pre-processing. We employ a fully convolutional neural network (FCN), and we combine the FCN with long short-term memory (LSTM) networks. The FCN can only handle monotemporal input data, while the FCN combined with LSTM can use sequential information (multitemporal). Besides, we provided fixed and variable sequences as training sequences for the combined FCN and LSTM approach. The former refers to using six defined satellite images, while the latter consists of image sequences from an extended training pool of ten images. Further, we propose measures for the robustness concerning the selection of Sentinel-2 image data as evaluation metrics. We can distinguish between actual land cover changes and misclassifications of the deep learning approaches with these metrics. According to the provided metrics, both multitemporal LSTM approaches outperform the monotemporal FCN approach, about 3 to 5 percentage points (p.p.). The LSTM approach trained on the variable sequences detects 3

p . p .

more land cover changes than the LSTM approach trained on the fixed sequences. Besides, applying our selected pre-processing improves the water classification and avoids reducing the dataset effectively by 17.6%. The presented LSTM approaches can be modified to provide applicability for a variable number of image sequences since we published the code of the deep learning models. The Sentinel-2 data and the ground truth are also freely available. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

17 pages, 4683 KiB

Open AccessArticle

Multi-Label Remote Sensing Image Scene Classification by Combining a Convolutional Neural Network and a Graph Neural Network

by Yansheng Li, Ruixian Chen, Yongjun Zhang, Mi Zhang and Ling Chen

Remote Sens. 2020, 12(23), 4003; https://doi.org/10.3390/rs12234003 - 07 Dec 2020

Cited by 46 | Viewed by 7056

Abstract

As one of the fundamental tasks in remote sensing (RS) image understanding, multi-label remote sensing image scene classification (MLRSSC) is attracting increasing research interest. Human beings can easily perform MLRSSC by examining the visual elements contained in the scene and the spatio-topological relationships of these visual elements. However, most of existing methods are limited by only perceiving visual elements but disregarding the spatio-topological relationships of visual elements. With this consideration, this paper proposes a novel deep learning-based MLRSSC framework by combining convolutional neural network (CNN) and graph neural network (GNN), which is termed the MLRSSC-CNN-GNN. Specifically, the CNN is employed to learn the perception ability of visual elements in the scene and generate the high-level appearance features. Based on the trained CNN, one scene graph for each scene is further constructed, where nodes of the graph are represented by superpixel regions of the scene. To fully mine the spatio-topological relationships of the scene graph, the multi-layer-integration graph attention network (GAT) model is proposed to address MLRSSC, where the GAT is one of the latest developments in GNN. Extensive experiments on two public MLRSSC datasets show that the proposed MLRSSC-CNN-GNN can obtain superior performance compared with the state-of-the-art methods. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

16 pages, 3709 KiB

Open AccessArticle

Optimizing the Recognition and Feature Extraction of Wind Turbines through Hybrid Semantic Segmentation Architectures

by Miguel-Ángel Manso-Callejo, Calimanut-Ionut Cira, Ramón Alcarria and José-Juan Arranz-Justel

Remote Sens. 2020, 12(22), 3743; https://doi.org/10.3390/rs12223743 - 13 Nov 2020

Cited by 12 | Viewed by 2737

Abstract

Updating the mapping of wind turbines farms—found in constant expansion—is important to predict energy production or to minimize the risk of these infrastructures during storms. This geoinformation is not usually provided by public mapping agencies, and the alternative sources are usually consortiums or individuals interested in mapping and study. However, they do not offer metadata or genealogy, and their quality is unknown. This article presents a methodology oriented to optimize the recognition and extraction of features (wind turbines) using hybrid architectures of semantic segmentation. The aim is to characterize the quality of these datasets and help to improve and update them automatically at a large-scale. To this end, we intend to evaluate the capacity of hybrid semantic segmentation networks trained to extract features representing wind turbines from high-resolution images and to characterize the positional accuracy and completeness of a dataset whose genealogy and quality are unknown. We built a training dataset composed of 5140 tiles of aerial images and their cartography to train six different neural network architectures. The networks were evaluated on five test areas (covering 520 km² of the Spanish territory) to identify the best segmentation architecture (in our case, LinkNet as base architecture and EfficientNet-b3 as the backbone). This hybrid segmentation model allowed us to characterize the completeness—both by commission and by omission—of the available georeferenced wind turbine dataset, as well as its geometric quality. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

21 pages, 3383 KiB

Open AccessArticle

Full Convolutional Neural Network Based on Multi-Scale Feature Fusion for the Class Imbalance Remote Sensing Image Classification

by Yuanyuan Ren, Xianfeng Zhang, Yongjian Ma, Qiyuan Yang, Chuanjian Wang, Hailong Liu and Quan Qi

Remote Sens. 2020, 12(21), 3547; https://doi.org/10.3390/rs12213547 - 29 Oct 2020

Cited by 31 | Viewed by 4723

Abstract

Remote sensing image segmentation with samples imbalance is always one of the most important issues. Typically, a high-resolution remote sensing image has the characteristics of high spatial resolution and low spectral resolution, complex large-scale land covers, small class differences for some land covers, vague foreground, and imbalanced distribution of samples. However, traditional machine learning algorithms have limitations in deep image feature extraction and dealing with sample imbalance issue. In the paper, we proposed an improved full-convolution neural network, called DeepLab V3+, with loss function based solution of samples imbalance. In addition, we select Sentinel-2 remote sensing images covering the Yuli County, Bayingolin Mongol Autonomous Prefecture, Xinjiang Uygur Autonomous Region, China as data sources, then a typical region image dataset is built by data augmentation. The experimental results show that the improved DeepLab V3+ model can not only utilize the spectral information of high-resolution remote sensing images, but also consider its rich spatial information. The classification accuracy of the proposed method on the test dataset reaches 97.97%. The mean Intersection-over-Union reaches 87.74%, and the Kappa coefficient 0.9587. The work provides methodological guidance to sample imbalance correction, and the established data resource can be a reference to further study in the future. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

Review

Jump to: Research, Other

41 pages, 1773 KiB

Open AccessReview

Deep Learning-Based Semantic Segmentation of Urban Features in Satellite Images: A Review and Meta-Analysis

by Bipul Neupane, Teerayut Horanont and Jagannath Aryal

Remote Sens. 2021, 13(4), 808; https://doi.org/10.3390/rs13040808 - 23 Feb 2021

Cited by 106 | Viewed by 14417

Abstract

Availability of very high-resolution remote sensing images and advancement of deep learning methods have shifted the paradigm of image classification from pixel-based and object-based methods to deep learning-based semantic segmentation. This shift demands a structured analysis and revision of the current status on the research domain of deep learning-based semantic segmentation. The focus of this paper is on urban remote sensing images. We review and perform a meta-analysis to juxtapose recent papers in terms of research problems, data source, data preparation methods including pre-processing and augmentation techniques, training details on architectures, backbones, frameworks, optimizers, loss functions and other hyper-parameters and performance comparison. Our detailed review and meta-analysis show that deep learning not only outperforms traditional methods in terms of accuracy, but also addresses several challenges previously faced. Further, we provide future directions of research in this domain. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

Other

Jump to: Research, Review

13 pages, 2307 KiB

Open AccessTechnical Note

RSCNN: A CNN-Based Method to Enhance Low-Light Remote-Sensing Images

by Linshu Hu, Mengjiao Qin, Feng Zhang, Zhenhong Du and Renyi Liu

Remote Sens. 2021, 13(1), 62; https://doi.org/10.3390/rs13010062 - 26 Dec 2020

Cited by 50 | Viewed by 4535

Abstract

Image enhancement (IE) technology can help enhance the brightness of remote-sensing images to obtain better interpretation and visualization effects. Convolutional neural networks (CNN), such as the Low-light CNN (LLCNN) and Super-resolution CNN (SRCNN), have achieved great success in image enhancement, image super resolution, and other image-processing applications. Therefore, we adopt CNN to propose a new neural network architecture with end-to-end strategy for low-light remote-sensing IE, named remote-sensing CNN (RSCNN). In RSCNN, an upsampling operator is adopted to help learn more multi-scaled features. With respect to the lack of labeled training data in remote-sensing image datasets for IE, we use real natural image patches to train firstly and then perform fine-tuning operations with simulated remote-sensing image pairs. Reasonably designed experiments are carried out, and the results quantitatively show the superiority of RSCNN in terms of structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) over conventional techniques for low-light remote-sensing IE. Furthermore, the results of our method have obvious qualitative advantages in denoising and maintaining the authenticity of colors and textures. Full article

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (14 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI