24 pages, 12355 KiB  
Article
Accuracy Comparison and Assessment of DSM Derived from GFDM Satellite and GF-7 Satellite Imagery
by Xiaoyong Zhu 1,2,*, Xinming Tang 1,2,3, Guo Zhang 1,2, Bin Liu 4 and Wenmin Hu 5
1 The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
2 The Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100094, China
3 College of Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
4 State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China
5 The National Joint Engineering Laboratory of Internet Applied Technology of Mines, China University of Mining and Technology, Xuzhou 221116, China
Remote Sens. 2021, 13(23), 4791; https://doi.org/10.3390/rs13234791 - 26 Nov 2021
Cited by 19 | Viewed by 3241
Abstract
Digital Surface Model (DSM) derived from high resolution satellite imagery is important for various applications. GFDM is China’s first civil optical remote sensing satellite with multiple agile imaging modes and sub-meter resolution. Its panchromatic resolution is 0.5 m and 1.68 m for multi-spectral [...] Read more.
Digital Surface Model (DSM) derived from high resolution satellite imagery is important for various applications. GFDM is China’s first civil optical remote sensing satellite with multiple agile imaging modes and sub-meter resolution. Its panchromatic resolution is 0.5 m and 1.68 m for multi-spectral images. Compared with the onboard stereo viewing instruments (0.8 m for forward image, 0.65 m for back image, and 2.6 m for back multi-spectrum images) of GF-7, a mapping satellite of China in the same period, their accuracy is very similar. However, the accuracy of GFDM DSM has not yet been verified or fully characterized, and the detailed difference between the two has not yet been assessed either. This paper evaluates the DSM accuracy generated by GFDM and GF-7 satellite imagery using high-precision reference DSM and the observations of Ground Control Points (GCPs) as the reference data. A method to evaluate the DSM accuracy based on regional DSM errors and GCPs errors is proposed. Through the analysis of DSM subtraction, profile lines, strips detection and residuals coupling differences, the differences of DSM overall accuracy, vertical accuracy, horizontal accuracy and the strips errors between GFDM DSM and GF-7 DSM are evaluated. The results show that the overall accuracy of both is close while the vertical accuracy is slightly different. When regional DSM is used as the benchmark, the GFDM DSM has a slight advantage in elevation accuracy, but there are some regular fluctuation strips with small amplitude. When GCPs are used as the reference, the elevation Root Mean Square Error (RMSE) of GFDM DSM is about 0.94 m, and that of GF-7 is 0.67 m. GF-7 DSM is more accurate, but both of the errors are within 1 m. The DSM image residuals of the GF-7 are within 0.5 pixel, while the residuals of GFDM are relatively large, reaching 0.8 pixel. Full article
Show Figures

Graphical abstract

15 pages, 28491 KiB  
Article
Towards a Deep-Learning-Based Framework of Sentinel-2 Imagery for Automated Active Fire Detection
by Qi Zhang 1,2, Linlin Ge 2, Ruiheng Zhang 1,*, Graciela Isabel Metternicht 3, Chang Liu 2 and Zheyuan Du 2
1 School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
2 School of Civil and Environmental Engineering, University of New South Wales, Sydney, NSW 2052, Australia
3 School of Biological, Earth and Environmental Sciences, University of New South Wales, Sydney, NSW 2052, Australia
Remote Sens. 2021, 13(23), 4790; https://doi.org/10.3390/rs13234790 - 26 Nov 2021
Cited by 30 | Viewed by 5176
Abstract
This paper proposes an automated active fire detection framework using Sentinel-2 imagery. The framework is made up of three basic parts including data collection and preprocessing, deep-learning-based active fire detection, and final product generation modules. The active fire detection module is developed on [...] Read more.
This paper proposes an automated active fire detection framework using Sentinel-2 imagery. The framework is made up of three basic parts including data collection and preprocessing, deep-learning-based active fire detection, and final product generation modules. The active fire detection module is developed on a specifically designed dual-domain channel-position attention (DCPA)+HRNetV2 model and a dataset with semi-manually annotated active fire samples is constructed over wildfires that commenced on the east coast of Australia and the west coast of the United States in 2019–2020 for the training process. This dataset can be used as a benchmark for other deep-learning-based algorithms to improve active fire detection accuracy. The performance of active fire detection is evaluated regarding the detection accuracy of deep-learning-based models and the processing efficiency of the whole framework. Results indicate that the DCPA and HRNetV2 combination surpasses DeepLabV3 and HRNetV2 models for active fire detection. In addition, the automated framework can deliver active fire detection results of Sentinel-2 inputs with coverage of about 12,000 km2 (including data download) in less than 6 min, where average intersections over union (IoUs) of 70.4% and 71.9% were achieved in tests over Australia and the United States, respectively. Concepts in this framework can be further applied to other remote sensing sensors with data acquisitions in SWIR-NIR-Red ranges and can serve as a powerful tool to deal with large volumes of high-resolution data used in future fire monitoring systems and as a cost-efficient resource in support of governments and fire service agencies that need timely, optimized firefighting plans. Full article
Show Figures

Figure 1

20 pages, 8562 KiB  
Article
Study on Spatiotemporal Evolution of the Yellow River Delta Coastline from 1976 to 2020
by Chengming Li, Lining Zhu *, Zhaoxin Dai and Zheng Wu
Chinese Academy of Surveying and Mapping, Beijing 100830, China
Remote Sens. 2021, 13(23), 4789; https://doi.org/10.3390/rs13234789 - 26 Nov 2021
Cited by 19 | Viewed by 3239
Abstract
The Yellow River Delta in China is the most active one for sea–land changes over all deltas worldwide, and its coastline evolution is critical to urban planning and environmental sustainability in coastal areas. Existing studies rarely used yearly temporal resolution, and lack more [...] Read more.
The Yellow River Delta in China is the most active one for sea–land changes over all deltas worldwide, and its coastline evolution is critical to urban planning and environmental sustainability in coastal areas. Existing studies rarely used yearly temporal resolution, and lack more detailed and quantitative analysis of coastline evolution characteristics. This paper used visual interpretation to extract the coastline of the Yellow River Delta in year interval Landsat images for 45 years from 1976 to 2020, and analyzed the spatiotemporal characteristics of the coastline evolution through statistical methods such as calculating change values and change rate. The main results are as follows: (1) overall, the coastline of the Yellow River Delta presented a spatial pattern involving northern landward retreat and southern seaward expansion. Since 1990, the Yellow River Delta has entered a period of decline. In addition, the length of the artificial coastline increased by about 55 km; (2) in the Qingshuigou region, the land area and the coastline length increased first and then stabilized. The southeastern part of the Qingshuigou was in a state of erosion, while the northeastern part was expanding toward the sea along the north direction; (3) in the Diaokou region, the land area has been decreasing, but the reduction rate has gradually slowed down. The main conclusions are as follows: (1) through the research on the evolution model and mechanism of the coastline of the Yellow River Delta, it was found that human factors and natural factors were the two major driving factors that affect the evolution of the coastline; (2) a river branch appeared in the northern part of the Qingshuigou region in 2014 and became a major branch in 2020, which would affect the development of the coastal region of Chengdao. This study is important for better understanding the evolution pattern of the Yellow River Delta coastline and will help to provide guidance for coastline management and resource exploitation. Full article
Show Figures

Graphical abstract

21 pages, 13120 KiB  
Article
PM2.5 Modeling and Historical Reconstruction over the Continental USA Utilizing GOES-16 AOD
by Xiaohe Yu 1, David J. Lary 2,* and Christopher S. Simmons 3
1 Geospatial Information Science, The University of Texas at Dallas, Richardson, TX 75080, USA
2 Hanson Center for Space Science, The University of Texas at Dallas, Richardson, TX 75080, USA
3 Cyber-Infrastructure & Research Services in the Information Technology Office, The University of Texas at Dallas, Richardson, TX 75080, USA
Remote Sens. 2021, 13(23), 4788; https://doi.org/10.3390/rs13234788 - 26 Nov 2021
Cited by 6 | Viewed by 3241
Abstract
In this study, we present a nationwide machine learning model for hourly PM2.5 estimation for the continental United States (US) using high temporal resolution Geostationary Operational Environmental Satellites (GOES-16) Aerosol Optical Depth (AOD) data, meteorological variables from the European Center for Medium [...] Read more.
In this study, we present a nationwide machine learning model for hourly PM2.5 estimation for the continental United States (US) using high temporal resolution Geostationary Operational Environmental Satellites (GOES-16) Aerosol Optical Depth (AOD) data, meteorological variables from the European Center for Medium Range Weather Forecasting (ECMWF) and ancillary data collected between May 2017 and December 2020. A model sensitivity analysis was conducted on predictor variables to determine the optimal model. It turns out that GOES16 AOD, variables from ECMWF, and ancillary data are effective variables in PM2.5 estimation and historical reconstruction, which achieves an average mean absolute error (MAE) of 3.0 μg/m3, and a root mean square error (RMSE) of 5.8 μg/m3. This study also found that the model performance as well as the site measured PM2.5 concentrations demonstrate strong spatial and temporal patterns. Specifically, in the temporal scale, the model performed best between 8:00 p.m. and 11:00 p.m. (UTC TIME) and had the highest coefficient of determination (R2) in Autumn and the lowest MAE and RMSE in Spring. In the spatial scale, the analysis results based on ancillary data show that the R2 scores correlate positively with the mean measured PM2.5 concentration at monitoring sites. Mean measured PM2.5 concentrations are positively correlated with population density and negatively correlated with elevation. Water, forests, and wetlands are associated with low PM2.5 concentrations, whereas developed, cultivated crops, shrubs, and grass are associated with high PM2.5 concentrations. In addition, the reconstructed PM2.5 surfaces serve as an important data source for pollution event tracking and PM2.5 analysis. For this purpose, from May 2017 to December 2020, hourly PM2.5 estimates were made for 10 km by 10 km and the PM2.5 estimates from August through November 2020 during the period of California Santa Clara Unite (SCU) Lightning Complex fires are presented. Based on the quantitative and visualization results, this study reveals that a number of large wildfires in California had a profound impact on the value and spatial-temporal distributions of PM2.5 concentrations. Full article
(This article belongs to the Special Issue Remote Sensing of Aerosols and Gases in Cities II)
Show Figures

Graphical abstract

19 pages, 4155 KiB  
Article
Geospatial Approaches to Monitoring the Spread of Invasive Species of Solidago spp.
by Štefan Koco 1,2, Anna Dubravská 1, Jozef Vilček 1,2 and Daniela Gruľová 3,*
1 Department of Geography and Applied Geoinformatics, Faculty of Humanities and Natural Sciences, University of Prešov, 17. Novembra 1, 08001 Prešov, Slovakia
2 National Agricultural and Food Centre, Soil Science and Conservation Research Institute, Raymanova 1, 08001 Prešov, Slovakia
3 Department of Ecology, Faculty of Humanities and Natural Sciences, University of Prešov, 17. Novembra 1, 08001 Prešov, Slovakia
Remote Sens. 2021, 13(23), 4787; https://doi.org/10.3390/rs13234787 - 26 Nov 2021
Cited by 8 | Viewed by 3150
Abstract
Global climate change influences plant invasion which spreads all over the Europe. Invasive plants are predominantly manifest negative impacts, which require increased attention not only from ecologists. The research examines the possibilities offered by geospatial technologies in mapping the spatial spread of invasive [...] Read more.
Global climate change influences plant invasion which spreads all over the Europe. Invasive plants are predominantly manifest negative impacts, which require increased attention not only from ecologists. The research examines the possibilities offered by geospatial technologies in mapping the spatial spread of invasive plants of the genus Solidago. Invasive plant population was investigated at two localities, Malý Šariš and Chminianska Nová Ves in Slovakia, as well as the mapping of the area by multispectral imaging to determine the spectral reflectance curve of the monitored plant species. Using spatial analyses in the geographic information system, we evaluated changes in the plant density in the two localities. Based on the obtained results, we found that the number of individuals (ramets) in the Malý Šariš is significantly increasing, while in the examined area of Chminianska Nová Ves, there is a decrease in the number of Solidago spp. in the last monitored year. At the same time, we can state that in the areas with the highest increase in the number of ramets, the highest plant density per hectare was also recorded. We can also say that due to the spectral proximity of the surrounding vegetation, the spectral resolution in four spectral bands is insufficient for the classification of multispectral records in the case of Solidago spp. and cannot replace the advantages of high spectral resolution hyperspectral imaging, which significantly refines the feature space for Solidago spp. and the surrounding vegetation. Full article
Show Figures

Graphical abstract

17 pages, 7765 KiB  
Article
Deep Learning Triplet Ordinal Relation Preserving Binary Code for Remote Sensing Image Retrieval Task
by Zhen Wang 1,2,*, Nannan Wu 1, Xiaohan Yang 1, Bingqi Yan 1 and Pingping Liu 2,3
1 School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China
2 Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
3 School of Computer Science and Technology, Jilin University, Changchun 130012, China
Remote Sens. 2021, 13(23), 4786; https://doi.org/10.3390/rs13234786 - 26 Nov 2021
Cited by 6 | Viewed by 2676
Abstract
As satellite observation technology rapidly develops, the number of remote sensing (RS) images dramatically increases, and this leads RS image retrieval tasks to be more challenging in terms of speed and accuracy. Recently, an increasing number of researchers have turned their attention to [...] Read more.
As satellite observation technology rapidly develops, the number of remote sensing (RS) images dramatically increases, and this leads RS image retrieval tasks to be more challenging in terms of speed and accuracy. Recently, an increasing number of researchers have turned their attention to this issue, as well as hashing algorithms, which map real-valued data onto a low-dimensional Hamming space and have been widely utilized to respond quickly to large-scale RS image search tasks. However, most existing hashing algorithms only emphasize preserving point-wise or pair-wise similarity, which may lead to an inferior approximate nearest neighbor (ANN) search result. To fix this problem, we propose a novel triplet ordinal cross entropy hashing (TOCEH). In TOCEH, to enhance the ability of preserving the ranking orders in different spaces, we establish a tensor graph representing the Euclidean triplet ordinal relationship among RS images and minimize the cross entropy between the probability distribution of the established Euclidean similarity graph and that of the Hamming triplet ordinal relation with the given binary code. During the training process, to avoid the non-deterministic polynomial (NP) hard problem, we utilize a continuous function instead of the discrete encoding process. Furthermore, we design a quantization objective function based on the principle of preserving triplet ordinal relation to minimize the loss caused by the continuous relaxation procedure. The comparative RS image retrieval experiments are conducted on three publicly available datasets, including UC Merced Land Use Dataset (UCMD), SAT-4 and SAT-6. The experimental results show that the proposed TOCEH algorithm outperforms many existing hashing algorithms in RS image retrieval tasks. Full article
(This article belongs to the Special Issue Deep Learning and Computer Vision in Remote Sensing)
Show Figures

Graphical abstract

18 pages, 7238 KiB  
Article
Temporal Information Extraction for Afforestation in the Middle Section of the Yarlung Zangbo River Using Time-Series Landsat Images Based on Google Earth Engine
by Hao Fu 1,2, Wei Zhao 1,3,*, Qiqi Zhan 1,4, Mengjiao Yang 1,4, Donghong Xiong 1,3 and Daijun Yu 2
1 Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, China
2 College of Earth Sciences, Chengdu University of Technology, Chengdu 610059, China
3 Kathmandu Center for Research and Education, Chinese Academy of Sciences-Tribhuvan University, Beijing 100101, China
4 University of Chinese Academy of Sciences, Beijing 100049, China
Remote Sens. 2021, 13(23), 4785; https://doi.org/10.3390/rs13234785 - 25 Nov 2021
Cited by 6 | Viewed by 3033
Abstract
Afforestation is one of the most efficient ways to control land desertification in the middle section of the Yarlung Zangbo River (YZR) valley. However, the lack of a quantitative way to record the planting time of artificial forest (AF) constrains further management for [...] Read more.
Afforestation is one of the most efficient ways to control land desertification in the middle section of the Yarlung Zangbo River (YZR) valley. However, the lack of a quantitative way to record the planting time of artificial forest (AF) constrains further management for these forests. The long-term archived Landsat images (including the Thematic Mapper (TM), Enhanced Thematic Mapper Plus (ETM+), and Operational Land Imager (OLI)) provide a good opportunity to capture the temporal change information about AF plantations. Under the condition that there would be an abrupt increasing trend in the normalized difference vegetation index (NDVI) time-series curve after afforestation, and this characteristic can be thought of as the indicator of the AF planting time. To extract the indicator, an algorithm based on the Google Earth Engine (GEE) for detecting this trend change point (TCP) on the maximum NDVI time series within the growing season (May to September) was proposed. In this algorithm, the time-series NDVI was initially smoothed and segmented into two subspaces. Then, a trend change indicator Sdiff was calculated with the difference between the fitting slopes of the subspaces before and after each target point. A self-adaptive method was applied to the NDVI series to find the right year with the maximum TCP, which is recorded as the AF planting time. Based on the proposed method, the AF planting time of the middle section of the YZR valley from 1988 to 2020 was derived. The detected afforestation temporal information was validated by 222 samples collected from the field survey, with a Pearson correlation coefficient of 0.93 and a root mean squared error (RMSE) of 2.95 years. Meanwhile, the area distribution of the AF planted each year has good temporal consistency with the implementation of the eco-reconstruction project. Overall, the study provides a good way to map AF planting times that is not only helpful for sustainable management of AF areas but also provides a basis for further research on the impact of afforestation on desertification control. Full article
(This article belongs to the Special Issue Remote Sensing of Ecosystems)
Show Figures

Figure 1

19 pages, 114272 KiB  
Article
Improving CPT-InSAR Algorithm with Adaptive Coherent Distributed Pixels Selection
by Longkai Dong 1,2,3, Chao Wang 1,2,3,*, Yixian Tang 1,2,3, Hong Zhang 1,2,3 and Lu Xu 1,2,3
1 Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2 International Research Center of Big Data for Sustainable Development Goals, Beijing 100094, China
3 University of Chinese Academy of Sciences, Beijing 100049, China
Remote Sens. 2021, 13(23), 4784; https://doi.org/10.3390/rs13234784 - 25 Nov 2021
Cited by 4 | Viewed by 2959
Abstract
The Coherent Pixels Technique Interferometry Synthetic Aperture Radar (CPT-InSAR) method of inverting surface deformation parameters by using high-quality measuring points possesses the flaw inducing sparse measuring points in non-urban areas. In this paper, we propose the Adaptive Coherent Distributed Pixel InSAR (ACDP-InSAR) method, [...] Read more.
The Coherent Pixels Technique Interferometry Synthetic Aperture Radar (CPT-InSAR) method of inverting surface deformation parameters by using high-quality measuring points possesses the flaw inducing sparse measuring points in non-urban areas. In this paper, we propose the Adaptive Coherent Distributed Pixel InSAR (ACDP-InSAR) method, which is an adaptive method used to extract Distributed Scattering Pixel (DSP) based on statistically homogeneous pixel (SHP) cluster tests and improves the phase quality of DSP through phase optimization, which cooperates with Coherent Pixel (CP) for the retrieval of ground surface deformation parameters. For a region with sparse CPs, DSPs and its SHPs are detected by double-layer windows in two steps, i.e., multilook windows and spatial filtering windows, respectively. After counting the pixel number of maximum SHP cluster (MSHPC) in the multilook window based on the Anderson–Darling (AD) test and filtering out unsuitable pixels, the candidate DSPs are selected. For the filtering window, the SHPs of MSHPC’ pixels within the new window, which is different compared with multilook windows, were detected, and the SHPs of DSPs were obtained, which were used for coherent estimation. In phase-linking, the results of Eigen decomposition-based Maximum likelihood estimator of Interferometric phase (EMI) results are used as the initial values of the phase triangle algorithm (PTA) for the purpose of phase estimation (hereafter called as PTA-EMI). The DSPs and estimated phase are then combined with CPs in order to retrievesurface deformation parameters. The method was validated by two cases. The results show that the density of measuring points increased approximately 6–10 times compared with CPT-InSAR, and the quality of the interferometric phase significantly improved after phase optimization. It was demonstrated that the method is effective in increasing measuring point density and improving phase quality, which increases significantly the detectability of the low coherence region. Compared with the Distributed Scatterer InSAR (DS-InSAR) technique, ACDP-InSAR possesses faster processing speed at the cost of resolution loss, which is crucial for Earth surface movement monitoring at large spatial scales. Full article
(This article belongs to the Special Issue Advances in InSAR Imaging and Data Processing)
Show Figures

Graphical abstract

15 pages, 4609 KiB  
Article
Intercalibration of Backscatter Measurements among Ku-Band Scatterometers Onboard the Chinese HY-2 Satellite Constellation
by Zhixiong Wang 1,2,*, Juhong Zou 3,4, Youguang Zhang 3,4, Ad Stoffelen 5, Wenming Lin 1, Yijun He 1, Qian Feng 3, Yi Zhang 3, Bo Mu 3 and Mingsen Lin 3
1 School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, China
2 Laboratory for Regional Oceanography and Numerical Modeling, Qingdao National Laboratory for Marine Science and Technology, Qingdao 266000, China
3 National Satellite Ocean Application Service, Beijing 100081, China
4 Southern Marine Science and Engineering Guangdong Laboratory, Guangzhou 511458, China
5 Royal Netherlands Meteorological Institute, 3730 AE De Bilt, The Netherlands
Remote Sens. 2021, 13(23), 4783; https://doi.org/10.3390/rs13234783 - 25 Nov 2021
Cited by 14 | Viewed by 2950
Abstract
The Chinese HY-2D satellite was launched on 19 May 2021, carrying a Ku-band scatterometer. Together with the operating scatterometers onboard the HY-2B and HY-2C satellites, the HY-2 series scatterometer constellation was built, constituting different satellite orbits and hence opportunity for mutual intercomparison and [...] Read more.
The Chinese HY-2D satellite was launched on 19 May 2021, carrying a Ku-band scatterometer. Together with the operating scatterometers onboard the HY-2B and HY-2C satellites, the HY-2 series scatterometer constellation was built, constituting different satellite orbits and hence opportunity for mutual intercomparison and intercalibration. To achieve intercalibration of backscatter measurements for these scatterometers, this study presents and performs three methods including: (1) direct comparison using collocated measurements, in which the nonlinear calibrations can also be derived; (2) intercalibration over the Amazon rainforest; (3) and the double-difference technique based on backscatter simulations over the global oceans, in which a geophysical model function and numerical weather prediction (NWP) model winds are needed. The results obtained using the three methods are comparable, i.e., the differences among them are within 0.1 dB. The intercalibration results are validated by comparing the HY-2 series scatterometer wind speeds with NWP model wind speeds. The curves of wind speed bias for the HY-2 series scatterometers are quite similar, particularly in wind speeds ranging from 4 to 20 m/s. Based on the well-intercalibrated backscatter measurements, consistent sea surface wind products from HY-2 series scatterometers can be produced, and greatly benefit data applications. Full article
(This article belongs to the Special Issue Remote Sensing of Ocean Surface Winds)
Show Figures

Figure 1

21 pages, 24683 KiB  
Article
Application of Supervised Machine Learning Technique on LiDAR Data for Monitoring Coastal Land Evolution
by Maurizio Barbarella 1, Alessandro Di Benedetto 2,* and Margherita Fiani 2
1 DICAM-ARCES, University of Bologna, 40136 Bologna, Italy
2 Department of Civil Engineering, University of Salerno, 84084 Fisciano, Italy
Remote Sens. 2021, 13(23), 4782; https://doi.org/10.3390/rs13234782 - 25 Nov 2021
Cited by 11 | Viewed by 3253
Abstract
Machine Learning (ML) techniques are now being used very successfully in predicting and supporting decisions in multiple areas such as environmental issues and land management. These techniques have also provided promising results in the field of natural hazard assessment and risk mapping. The [...] Read more.
Machine Learning (ML) techniques are now being used very successfully in predicting and supporting decisions in multiple areas such as environmental issues and land management. These techniques have also provided promising results in the field of natural hazard assessment and risk mapping. The aim of this work is to apply the Supervised ML technique to train a model able to classify a particular gravity-driven coastal hillslope geomorphic model (slope-over-wall) involving most of the soft rocks of Cilento (southern Italy). To train the model, only geometric data have been used, namely morphometric feature maps computed on a Digital Terrain Model (DTM) derived from Light Detection and Ranging (LiDAR) data. Morphometric maps were computed using third-order polynomials, so as to obtain products that best describe landforms. Not all morphometric parameters from literature were used to train the model, the most significant ones were chosen by applying the Neighborhood Component Analysis (NCA) method. Different models were trained and the main indicators derived from the confusion matrices were compared. The best results were obtained using the Weighted k-NN model (accuracy score = 75%). Analysis of the Receiver Operating Characteristic (ROC) curves also shows that the discriminating capacity of the test reached percentages higher than 95%. The model, resulting more accurate in the training area, will be extended to similar areas along the Tyrrhenian coastal land. Full article
Show Figures

Figure 1

19 pages, 5529 KiB  
Article
Combinational Fusion and Global Attention of the Single-Shot Method for Synthetic Aperture Radar Ship Detection
by Libo Xu 1,2,*, Chaoyi Pang 1,2,3, Yan Guo 1,2 and Zhenyu Shu 1,2
1 School of Computing and Data Engineering, Ningbo Institute of Technology, Zhejiang University, Ningbo 315000, China
2 School of Computing and Data Engineering, NingboTech University, Ningbo 315000, China
3 Faculty of Engineering and Information Technology, Griffith University, Brisbane 4215, Australia
Remote Sens. 2021, 13(23), 4781; https://doi.org/10.3390/rs13234781 - 25 Nov 2021
Cited by 3 | Viewed by 2439
Abstract
Synthetic Aperture Radar (SAR), an active remote sensing imaging radar technology, has certain surface penetration ability and can work all day and in all weather conditions. It is widely applied in ship detection to quickly collect ship information on the ocean surface from [...] Read more.
Synthetic Aperture Radar (SAR), an active remote sensing imaging radar technology, has certain surface penetration ability and can work all day and in all weather conditions. It is widely applied in ship detection to quickly collect ship information on the ocean surface from SAR images. However, the ship SAR images are often blurred, have large noise interference, and contain more small targets, which pose challenges to popular one-stage detectors, such as the single-shot multi-box detector (SSD). We designed a novel network structure, a combinational fusion SSD (CF-SSD), based on the framework of the original SSD, to solve these problems. It mainly includes three blocks, namely a combinational fusion (CF) block, a global attention module (GAM), and a mixed loss function block, to significantly improve the detection accuracy of SAR images and remote sensing images and maintain a fast inference speed. The CF block equips every feature map with the ability to detect objects of all sizes at different levels and forms a consistent and powerful detection structure to learn more useful information for SAR features. The GAM block produces attention weights and considers the channel attention information of various scale feature information or cross-layer maps so that it can obtain better feature representations from the global perspective. The mixed loss function block can better learn the positions of the truth anchor boxes by considering corner and center coordinates simultaneously. CF-SSD can effectively extract and fuse the features, avoid the loss of small or blurred object information, and precisely locate the object position from SAR images. We conducted experiments on the SAR ship dataset SSDD, and achieved a 90.3% mAP and fast inference speed close to that of the original SSD. We also tested our model on the remote sensing dataset NWPU VHR-10 and the common dataset VOC2007. The experimental results indicate that our proposed model simultaneously achieves excellent detection performance and high efficiency. Full article
(This article belongs to the Special Issue Deep Learning for Radar and Sonar Image Processing)
Show Figures

Graphical abstract

27 pages, 13761 KiB  
Article
Arctic Tundra Land Cover Classification on the Beaufort Coast Using the Kennaugh Element Framework on Dual-Polarimetric TerraSAR-X Imagery
by Willeke A’Campo 1, Annett Bartsch 2, Achim Roth 3, Anna Wendleder 3, Victoria S. Martin 4, Luca Durstewitz 1, Rachele Lodi 5,6, Julia Wagner 1,7 and Gustaf Hugelius 1,7,*
1 Department of Physical Geography, Stockholm University, 10691 Stockholm, Sweden
2 b.geos, 2100 Korneuburg, Austria
3 German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), 82234 Wessling, Germany
4 Centre for Microbiology and Environmental Systems Science, Division of Terrestrial Ecosystem Research, University of Vienna, 1030 Wien, Austria
5 National Research Council, Institute of Polar Science (ISP-CNR), 30172 Venezia, Italy
6 Department of Environmental Sciences, Informatics and Statistics, University Ca’ Foscari of Venice, 30172 Venezia, Italy
7 Bolin Centre for Climate Research, Stockholm University, 10691 Stockholm, Sweden
Remote Sens. 2021, 13(23), 4780; https://doi.org/10.3390/rs13234780 - 25 Nov 2021
Cited by 10 | Viewed by 4187
Abstract
Arctic tundra landscapes are highly complex and are rapidly changing due to the warming climate. Datasets that document the spatial and temporal variability of the landscape are needed to monitor the rapid changes. Synthetic Aperture Radar (SAR) imagery is specifically suitable for monitoring [...] Read more.
Arctic tundra landscapes are highly complex and are rapidly changing due to the warming climate. Datasets that document the spatial and temporal variability of the landscape are needed to monitor the rapid changes. Synthetic Aperture Radar (SAR) imagery is specifically suitable for monitoring the Arctic, as SAR, unlike optical remote sensing, can provide time series regardless of weather and illumination conditions. This study examines the potential of seasonal backscatter mechanisms in Arctic tundra environments for improving land cover classification purposes by using a time series of HH/HV TerraSAR-X (TSX) imagery. A Random Forest (RF) classification was applied on multi-temporal Sigma Nought intensity and multi-temporal Kennaugh matrix element data. The backscatter analysis revealed clear differences in the polarimetric response of water, soil, and vegetation, while backscatter signal variations within different vegetation classes were more nuanced. The RF models showed that land cover classes could be distinguished with 92.4% accuracy for the Kennaugh element data, compared to 57.7% accuracy for the Sigma Nought intensity data. Texture predictors, while improving the classification accuracy on the one hand, degraded the spatial resolution of the land cover product. The Kennaugh elements derived from TSX winter acquisitions were most important for the RF model, followed by the Kennaugh elements derived from summer and autumn acquisitions. The results of this study demonstrate that multi-temporal Kennaugh elements derived from dual-polarized X-band imagery are a powerful tool for Arctic tundra land cover mapping. Full article
Show Figures

Graphical abstract

19 pages, 7032 KiB  
Article
An Improved Swin Transformer-Based Model for Remote Sensing Object Detection and Instance Segmentation
by Xiangkai Xu, Zhejun Feng, Changqing Cao *, Mengyuan Li, Jin Wu, Zengyan Wu, Yajie Shang and Shubing Ye
School of Physics and Optoelectronic Engineering, Xidian University, 2 South TaiBai Road, Xi’an 710071, China
Remote Sens. 2021, 13(23), 4779; https://doi.org/10.3390/rs13234779 - 25 Nov 2021
Cited by 137 | Viewed by 15227
Abstract
Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies [...] Read more.
Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask APS by 3.6%, AP by 1.1% and APS by 4.6%, demonstrating its effectiveness and feasibility. Full article
(This article belongs to the Special Issue Deep Learning and Computer Vision in Remote Sensing)
Show Figures

Graphical abstract

24 pages, 7036 KiB  
Article
Evaluation and Analysis of Poverty-Stricken Counties under the Framework of the UN Sustainable Development Goals: A Case Study of Hunan Province, China
by Yanjun Wang 1,2,3,*, Mengjie Wang 1,2,3, Bo Huang 4, Shaochun Li 1,2,3 and Yunhao Lin 1,2,3
1 Hunan Provincial Key Laboratory of Geo-Information Engineering in Surveying, Mapping and Remote Sensing, Hunan University of Science and Technology, Xiangtan 411201, China
2 National-Local Joint Engineering Laboratory of Geo-Spatial Information Technology, Hunan University of Science and Technology, Xiangtan 411201, China
3 School of Earth Sciences and Geospatial Information Engineering, Hunan University of Science and Technology, Xiangtan 411201, China
4 Department of Geography and Resource Management, The Chinese University of Hong Kong, Shatin, Hong Kong 999077, China
Remote Sens. 2021, 13(23), 4778; https://doi.org/10.3390/rs13234778 - 25 Nov 2021
Cited by 15 | Viewed by 3808
Abstract
Eliminating all forms of poverty in the world is the first United Nations Sustainable Development Goal (SDG). Developing a scientific and feasible method for monitoring and evaluating local poverty is important for the implementation of the SDG agenda. Based on the 2030 United [...] Read more.
Eliminating all forms of poverty in the world is the first United Nations Sustainable Development Goal (SDG). Developing a scientific and feasible method for monitoring and evaluating local poverty is important for the implementation of the SDG agenda. Based on the 2030 United Nations SDGs, in this paper, a quantitative evaluation model is built and applied to all poverty-stricken counties in Hunan Province. First, based on the SDG global index framework and local index system of China, a local SDG index system for poverty-related goals is designed, and the weights of the indexes are derived using an entropy method. The scores obtained for counties and districts with data available are then taken as the true value for the poverty assessment. Second, using National Polar-orbiting Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) nighttime light images and land use and digital elevation model data, six factors, including socioeconomic, land cover, terrain and traffic factors, are extracted. Third, we then construct multiple linear evaluation models of poverty targets defined by the SDGs and machine learning evaluation models, including regression trees, support vector machines, Gaussian process regressions and ensemble trees. Last, combined with statistical data of poverty-stricken counties in Hunan Province, model validation and accuracy evaluation are carried out. The results show that the R2 and relative error of the localized, multiple linear evaluation model, including all six factors, are 0.76 and 19.12%, respectively. The poverty-stricken counties in Hunan Province were spatially aggregated and distributed mainly in the southeastern and northwestern regions. The proposed method for regional poverty assessment based on multisource geographic data provides an effective poverty monitoring reference scheme for the implementation of the poverty eradication goals in the 2030 agenda. Full article
Show Figures

Figure 1

24 pages, 13296 KiB  
Article
Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization
by Li Yan, Yao Li and Hong Xie *
1 School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China
Li Yan and Yao Li contributed equally to this paper.
Remote Sens. 2021, 13(23), 4777; https://doi.org/10.3390/rs13234777 - 25 Nov 2021
Cited by 6 | Viewed by 2906
Abstract
With the development of UAV and oblique photogrammetry technology, the multi-view stereo image has become an important data source for 3D urban reconstruction, and the surface meshes generated by it have become a common way to represent the building surface model due to [...] Read more.
With the development of UAV and oblique photogrammetry technology, the multi-view stereo image has become an important data source for 3D urban reconstruction, and the surface meshes generated by it have become a common way to represent the building surface model due to their high geometric similarity and high shape representation ability. However, due to the problem of data quality and lack of building structure information in multi-view stereo image data sources, it is a huge challenge to generate simplified polygonal models from building surface meshes with high data redundancy and fuzzy structural boundaries, along with high time consumption, low accuracy, and poor robustness. In this paper, an improved mesh representation strategy based on 1-ring patches is proposed, and the topology validity is improved on this basis. Experimental results show that our method can reconstruct the concise, manifold, and watertight surface models of different buildings, and it can improve the processing efficiency, parameter adaptability, and model quality. Full article
(This article belongs to the Special Issue 3D City Modelling and Change Detection Using Remote Sensing Data)
Show Figures

Figure 1