WorldView-2 Satellite Images Research Articles

GSA-SiamNet: A Siamese Network with Gradient-Based Spatial Attention for Pan-Sharpening of Multi-Spectral Images

Pan-sharpening is a fusion process that combines a low-spatial resolution, multi-spectral image that has rich spectral characteristics with a high-spatial resolution panchromatic (PAN) image that lacks spectral characteristics. Most previous learning-based approaches rely on the scale-shift assumption, which may not be applicable in the full-resolution domain. To solve this issue, we regard pan-sharpening as a multi-task problem and propose a Siamese network with Gradient-based Spatial Attention (GSA-SiamNet). GSA-SiamNet consists of four modules: a two-stream feature extraction module, a feature fusion module, a gradient-based spatial attention (GSA) module, and a progressive up-sampling module. In the GSA module, we use Laplacian and Sobel operators to extract gradient information from PAN images. Spatial attention factors, learned from the gradient prior, are multiplied during the feature fusion, up-sampling, and reconstruction stages. These factors help to keep high-frequency information on the feature map as well as suppress redundant information. We also design a multi-resolution loss function that guides the training process under the constraints of both reduced- and full-resolution domains. The experimental results on WorldView-3 satellite images obtained in Moscow and San Juan demonstrate that our proposed GSA-SiamNet is superior to traditional and other deep learning-based methods.

Pan-Sharpening Network of Multi-Spectral Remote Sensing Images Using Two-Stream Attention Feature Extractor and Multi-Detail Injection (TAMINet)

Achieving a balance between spectral resolution and spatial resolution in multi-spectral remote sensing images is challenging due to physical constraints. Consequently, pan-sharpening technology was developed to address this challenge. While significant progress was recently achieved in deep-learning-based pan-sharpening techniques, most existing deep learning approaches face two primary limitations: (1) convolutional neural networks (CNNs) struggle with long-range dependency issues, and (2) significant detail loss during deep network training. Moreover, despite these methods’ pan-sharpening capabilities, their generalization to full-sized raw images remains problematic due to scaling disparities, rendering them less practical. To tackle these issues, we introduce in this study a multi-spectral remote sensing image fusion network, termed TAMINet, which leverages a two-stream coordinate attention mechanism and multi-detail injection. Initially, a two-stream feature extractor augmented with the coordinate attention (CA) block is employed to derive modal-specific features from low-resolution multi-spectral (LRMS) images and panchromatic (PAN) images. This is followed by feature-domain fusion and pan-sharpening image reconstruction. Crucially, a multi-detail injection approach is incorporated during fusion and reconstruction, ensuring the reintroduction of details lost earlier in the process, which minimizes high-frequency detail loss. Finally, a novel hybrid loss function is proposed that incorporates spatial loss, spectral loss, and an additional loss component to enhance performance. The proposed methodology’s effectiveness was validated through experiments on WorldView-2 satellite images, IKONOS, and QuickBird, benchmarked against current state-of-the-art techniques. Experimental findings reveal that TAMINet significantly elevates the pan-sharpening performance for large-scale images, underscoring its potential to enhance multi-spectral remote sensing image quality.

Combining Moderate and High Resolution of Satellite Images for Characterizing Suitable Habitat for Vegetation and Wildlife

Combining different resolution of remote sensing satellites becomes a unique approach for vegetation and wildlife habitat assessment study. Remote sensing technology can reach land and water on the Earth's surface, and it can interpret signals from spectral responses. When these techniques are combined with Geographical Information Systems (GIS), land can be monitored in a variety of ways. Meanwhile, changes in land use led to changes in vegetation on the ground, with natural vegetation being removed from natural forests, leaving a degraded forest. This issue was not investigated for assessing habitat suitability for important plantations such as Eucalyptus plantation. Therefore, the study employed remote sensing and Geographical Information System (GIS) to model suitability of habitat to live and to survive in the Eucalyptus plantation. Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) derived from a mathematical equation can demonstrate intensity of greenness of green vegetation in particular area and time, and availability of soil moisture, respectively, is very suitable to model the greenness of the area. WorldView-2 satellite image was pre-proceed, proceed, and classified to produce land use indicator in Sabah Softwoods Berhad plantation majoring Eucalyptus spp. tree planted in Tawau, Sabah. Sentinel and Landsat 8 image were used for vegetation and water stress indicator were downloaded from Land Viewer application. Net Primary Productivity (NPP) at monthly scale was also calculated and ranked the productivity for the suitability mapping. Climatic condition based on monthly precipitation and seasonality derived from ASEAN Specialized Meteorological Centre (ASMC) was employed for ranking its suitability value. In this study, natural forest and oil palm plantation is tested to developed suitability map for vegetation and wildlife habitat to live with. All indicators were ranked 10 to 40 presenting benefit and usefulness of the indicator to vegetation and wildlife in the study area. Then, final classification was made from accumulation of those indicators into 0 to 200 (Not suitable to Highly suitable). The results showed 59.9% of the area classified as moderately suitable, 36.9% highly suitable, 3.2% least suitable and no area was classified as not suitable. This type of study assisted forest managers and policymakers for better managing of their forests for better life of trees and wildlife under their management. The methodology adapted in the study is ecologically sounded and economically viable to be modified and complied in Sustainable Forest Management (SFM) in Malaysia and other tropical forest regions.

Multi-Fusion algorithms for Detecting Land Surface Pattern Changes Using Multi-High Spatial Resolution Images and Remote Sensing Analysis

Producing accurate Land-Use and Land-Cover (LU/LC) maps using low-spatial-resolution images is a difficult task. Pan-sharpening is crucial for estimating LU/LC patterns. This study aimed to identify the most precise procedure for estimating LU/LC by adopting two fusion approaches, namely Color Normalized Brovey (BM) and Gram-Schmidt Spectral Sharpening (GS), on high-spatial-resolution Multi-sensor and Multi-spectral images, such as (1) the Unmanned Aerial Vehicle (UAV) system, (2) the WorldView-2 satellite system, and (3) low-spatial-resolution images like the Sentinel-2 satellite, to generate six levels of fused images with the three original multi-spectral images. The Maximum Likelihood method (ML) was used for classifying all nine images. A confusion matrix was used to evaluate the accuracy of each single classified image. The obtained results were statistically compared to determine the most reliable, accurate, and appropriate LU/LC map and procedure. It was found that applying GS to the fused image, which integrated WorldView-2 and Sentinel-2 satellite images and was classified by the ML method, produced the most accurate results. This procedure has an overall accuracy of 88.47% and a kappa coefficient of 0.85. However, the overall accuracies of the three classified multispectral images range between 86.84% to 76.49%. Furthermore, the accuracy assessment of the fused images by the Brovey method and the rest of the GS method and classified by the ML method ranges between 85.75% to 76.68%. This proposed procedure shows a lot of promise in the academic sphere for mapping LU/LC. Previous researchers have mostly used satellite images or datasets with similar spatial and spectral resolution, at least for tropical areas like the study area of this research, to detect land surface patterns. However, no one has previously investigated and examined the use and application of different datasets that have different spectral and spatial resolutions and their accuracy for mapping LU/LC. This study has successfully adopted different datasets provided by different sensors with varying spectral and spatial levels to investigate this. Doi: 10.28991/ESJ-2023-07-04-013 Full Text: PDF

Multitemporal modeling and simulation of the complex dynamics in urban wetlands: the case of Bogota, Colombia

Urban wetlands are essential to the longstanding health and well-being of cities. Acknowledged as rich in biodiversity and highly productive ecosystems, they provide ecosystem services represented in aspects such as air purification, urban climate regulation, physical and mental health, recreation, and contemplation, among a wide variety of other goods and services on which the quality of life of the inhabitants of large cities such as Bogota depends largely. We used cellular automata to model and simulate urban wetland changes in Bogota, Colombia. The study applied the coupled Markov-Future Land Use Simulation (FLUS) model to simulate and analyze land use/land cover (LULC) change over 20 years. First, we used an orthomosaic (1998) and two WorldView-2 satellite images (2004 and 2010), to detect land cover changes. Then, using the artificial neural network FLUS module, we calculated the relationships between land classes and associated drivers and estimated the probability of occurrence of each land class. Finally, we applied Intensity Analysis to examine the observed and projected LULC change (1998–2034). Results indicate that gains in areas of crops and pastures are at the expense of wetlands. In addition, simulation outputs show that wetlands will likely represent less than 2% of the total study area in 2034, representing a 14% decrease in 24 years. The importance of this project lies in its potential contribution to the decision-making process within the city and as an instrument of natural resource management. Additionally, the results of this study could contribute to the United Nations Sustainable Development Goal 6, “Clean water and sanitation," and climate change mitigation.

An object-based image analysis approach for comparing tree detection from satellite imagery at different scales; A case study in Sukumba Mali

This paper combines an object-based image analysis (OBIA) approach, with markov-random field based-super resolution mapping (MRF-SRM) technique to extract individual tree objects from satellite imagery. Extraction of individual trees in urban and developing cities using satellite imageries has been quite challenging and a subject of active research with many approaches to it. The study area is a part of Sukumba village located in Koutiala district, Mali. The aim is to evaluate the performance comparison of the combined MRF-SRM approach, which was demonstrated for each combination of scale factor and class separability. Due to varying contrast sensitivity, there exist a general limitation in the spatial distribution of land cover data sets derived from most coarse and fine resolution satellite imageries. A 10 m spatial resolution Sentinel-2 and 2 m spatial resolution Worldview-3 satellite images were used for the study. First, the pixel based MRF-SRM classification technique of Tolpekin and Stein, 2009 was applied on both images. Subsequently, the classified SRM thematic results were partitioned into objects (segments) using region growing segmentation algorithm as post a classification procedure. Finally, validation and comparison of the resulting tree objects was done using an object based image analysis approach to determine existential (TP), extensional (FP) and positional (PA) accuracy. For Sentinel-2 image and out of 1787 reference objects, 1214 (TP) was detected and 573 (FP) was undetected. The PA is 6.504 m out of 10 m, total detection error is 0.467 m and the final detection accuracy is 68%. Similarly, for Worldview-3 image and out of 1787 reference objects, 1772 (TP) was detected and 15 (FP) was undetected. The PA is 1.714 m out of 2 m, total detection error is 0.318 m and the final detection accuracy is 99%. The successful approach used in this study will support the capacity of monitoring agricultural change in data sparse regions and developing countries.

Exploratory Mapping of Blue Ice Regions in Antarctica Using Very High-Resolution Satellite Remote Sensing Data

Mapping spatiotemporal changes in the distribution of blue ice regions (BIRs) in Antarctica requires repeated, precise, and high-resolution baseline maps of the blue ice extent. This study demonstrated the design and application of a newly-developed semi-automatic method to map BIRs in the Antarctic environment using very high-resolution (VHR) WorldView-2 (WV-2) satellite images. We discussed the potential of VHR satellite data for the mapping of BIRs in the Antarctic environment using a customized normalized-difference blue-ice index (NDBI) method devised using yellow, green, and near-infrared spectral bands of WV-2 data. We compared the viability of the newly developed customized NDBI approach against state-of-the-art target detection (TD), spectral processing (SP) and pixel-wise supervised (PSC) feature extraction (FE) approaches. Four semi-automatic FE approaches (three existing plus one newly developed) consisting of 16 standalone FE methods (12 existing + four customized) were evaluated using an extensive quantitative and comparative assessment for mapping BIRs in the vicinity of Schirmacher Oasis, on the continental Antarctic coastline. The results suggested that the customized NDBI approach gave a superior performance and the highest statistical stability when compared with existing FE techniques. The customized NDBI generally rendered the lowest level of misclassification (average RMSE = 654.48 ± 58.26 m2), followed by TD (average RMSE = 987.81 ± 55.05 m2), SP (average RMSE = 1327.09 ± 127.83 m2) and PSC (average RMSE = 2259.43 ± 115.36 m2) for mapping BIRs. Our results indicated that the use of the customized NDBI approach can greatly improve the semi-automatic mapping of BIRs in the Antarctic environment. This study presents the first refined map of distribution of BIRs around the Schirmacher Oasis. The total area of blue ice in the study area was estimated to be 106.875 km2, approximately 61% of the study area. The WV-2 derived BIR map area presented in this study locally refined the existing BIR map derived using Landsat Enhanced Thematic Mapper Plus (ETM+) and the Moderate Resolution Imaging Spectroradiometer (MODIS)-based mosaic of Antarctica (MOA) dataset by ~31% (~33.40 km2). Finally, we discussed the practical challenges and future directions in mapping BIRs across Antarctica.

Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation

Deriving the thematic accuracy of models is a fundamental part of image classification analyses. K-fold cross-validation (KCV), as an accuracy assessment technique, can be biased because existing built-in algorithms of software solutions do not handle the high autocorrelation of remotely sensed images, leading to overestimation of accuracies. We aimed to quantify the magnitude of the overestimation of KCV-based accuracies and propose a method to overcome this problem with the example of rooftops using a WorldView-2 (WV2) satellite image, and two orthophotos. Random split to training/testing subsets, independent testing and different types of repeated KCV sampling strategies were used to generate input datasets for classification. Results revealed that applying the random splitting of reference data to training/testing subsets and KCV methods had significantly biased the accuracies by up to 17%; overall accuracies (OAs) can incorrectly reach >99%. We found that repeated KCV can provide similar results to independent testing when spatial sampling is applied with a sufficiently large distance threshold (in our case 10 m). Coarser resolution of WV2 ensured more reliable results (up to a 5–9% increase in OA) than orthophotos. Object-based pixel purity of buildings showed that when using a majority filter for at least of 50% of objects the final accuracy approached 100% with each sampling method. The final conclusion is that KCV-based modelling ensures better accuracy than single models (with better pixel purity on the object level), but the accuracy metrics without spatially filtered sampling are not reliable.

Insulator Detection for High-Resolution Satellite Images Based on Deep Learning

The detection of electrical insulators in Unmanned Aerial Vehicle (UAV) images using deep learning has made great progress in recent years, but little research has been conducted in the same field in remote sensing (RS) images. In this paper, a novel method was proposed to detect insulators on 500kV transmission towers in RS images. The proposed method consists of three components including 1) a super-resolution (SR) network to improve image resolution, 2) an object detection model to detect 110kV, 220kV and 500kV electrical power towers along transmission pipelines and 3) a semantic segmentation network to identify insulators on the detected 500kV towers. In addition, the online hard example mining (OHEM) method and class weight calculation method were utilized to handle the imbalanced data among different classes during training. The proposed model was evaluated on SuperView-1 and WorldView-3 satellite images collected in 4 regions. Experiment results show that the proposed method can effectively detect insulators in high-resolution satellite images and achieved the highest F1 score of 0.7952. The codes are available at https://github.com/hardworking-jws/insulator-detection-remote-sensing.

Multispectral Characteristics of Glacier Surface Facies (Chandra-Bhaga Basin, Himalaya, and Ny-Ålesund, Svalbard) through Investigations of Pixel and Object-Based Mapping Using Variable Processing Routines

Fundamental image processing methods, such as atmospheric corrections and pansharpening, influence the signal of the pixel. This morphs the spectral signature of target features causing a change in both the final spectra and the way different mapping methods may assign thematic classes. In the current study, we aim to identify the variations induced by popular image processing methods in the spectral reflectance and final thematic maps of facies. To this end, we have tested three different atmospheric corrections: (a) Quick Atmospheric Correction (QUAC), (b) Dark Object Subtraction (DOS), and (c) Fast Line-of-Sight Atmospheric Analysis of Hypercubes (FLAASH), and two pansharpening methods: (a) Hyperspherical Color Sharpening (HCS) and (b) Gram–Schmidt (GS). WorldView-2 and WorldView-3 satellite images over Chandra-Bhaga Basin, Himalaya, and Ny-Ålesund, Svalbard are tested via spectral subsets in traditional (BGRN1), unconventional (CYRN2), visible to near-infrared (VNIR), and the complete available spectrum (VNIR_SWIR). Thematic mapping was comparatively performed using 12 pixel-based (PBIA) algorithms and 3 object-based (GEOBIA) rule sets. Thus, we test the impact of varying image processing routines, effectiveness of specific spectral bands, utility of PBIA, and versatility of GEOBIA for mapping facies. Our findings suggest that the image processing routines exert an extreme impact on the end spectral reflectance. DOS delivers the most reliable performance (overall accuracy = 0.64) averaged across all processing schemes. GEOBIA delivers much higher accuracy when the QUAC correction is employed and if the image is enhanced by GS pansharpening (overall accuracy = 0.79). SWIR bands have not enhanced the classification results and VNIR band combination yields superior performance (overall accuracy = 0.59). The maximum likelihood classifier (PBIA) delivers consistent and reliable performance (overall accuracy = 0.61) across all processing schemes and can be used after DOS correction without pansharpening, as it deteriorates spectral information. GEOBIA appears to be robust against modulations in atmospheric corrections but is enhanced by pansharpening. When utilizing GEOBIA, we find that a combination of spatial and spectral object features (rule set 3) delivers the best performance (overall accuracy = 0.86), rather than relying only on spectral (rule set 1) or spatial (rule set 2) object features. The multiresolution segmentation parameters used here may be transferable to other very high resolution (VHR) VNIR mapping of facies as it yielded consistent objects across all processing schemes.

A New Method for Automated Monitoring of Road Pavement Aging Conditions Based on Recurrent Neural Network

The automated monitoring of road pavement conditions is a challenging subject in intelligent transportation. However, the existing studies mostly focus on extracting pavement damages such as cracks, while the pavement aging conditions are still less investigated. In this paper, a novel method based on a modified recurrent neural network is designed for automated monitoring of asphalt pavement aging phenomena from fine-resolution satellite imagery. A spectral augmentation method is proposed to enhance the spectral details of the road pavements. A novel loss function is also proposed to improve the bi-directional gated recurrent unit (Bi-GRU) network in order to better classify different degrees of road pavement aging and non-pavement objects. In order to demonstrate the outperformance of the modified network Bi-GRU+, the Worldview-2 satellite image (16360*7728) covering 16 asphalt roads in the southwestern suburb of Beijing City is used. The results show that the proposed approach has better performance than existing machine learning methods, with an overall accuracy of 98.16% and a Kappa coefficient of 0.97. The overall processing time of the proposed method is 7836 seconds in our case study. The proposed method is efficient for large-scale monitoring of road health conditions from fine-resolution satellite imagery. It can become a part of intelligent transportation and provide a new foundation for large-range automated monitoring of road pavement aging conditions.

Monitoring green biomass utilizing remote sensing techniques for agriculture and forest areas in East Malaysia

Forests and agricultural plantations are vegetated areas that play an important role in catering to human needs. The characteristics of the two lands can be recognized by utilizing remote sensing techniques of WorldView-2 satellite images as green biomass monitoring tools. The research was undertaken in Sabah Softwoods Berhad (SSB) forest plantation, East Malaysia, to analyze land use in the high functionality areas. Aside from the social benefits, there has been a lack of research conducted to estimate the areas’ Net Primary Productivity (NPP) using remote sensing of biophysical characteristics. The NPP quantifies the biomass generated by the green plants, which provides the chemical energy that drives most of the biotic processes on the Earth. The NPP calculated from the study for all land features in the study areas ranged from 39.33 gCm−2 month−1 to 1498.00 gCm-2 month-1. This work has established a new NPP assessment for all land features in the Brumas forest plantation in East Malaysia. Because NPP is an estimate of the earth’s living biomass, this type of approach should be used to develop biomass maps to meet human requirements on the planet.

Integrated usage of historical geospatial data and modern satellite images reveal long-term land use/cover changes in Bursa/Turkey, 1858–2020

Land surface of the Earth has been changing as a result of human induced activities and natural processes. Accurate representation of landscape characteristics and precise determination of spatio-temporal changes provide valuable inputs for environmental models, landscape and urban planning, and historical land cover change analysis. This study aims to determine historical land use and land cover (LULC) changes using multi-modal geospatial data, which are the cadastral maps produced in 1858, monochrome aerial photographs obtained in 1955, and multi-spectral WorldView-3 satellite images of 2020. We investigated two pilot regions, Aksu and Kestel towns in Bursa/Turkey, to analyze the long-term LULC changes quantitatively and to understand the driving forces that caused the changes. We propose methods to facilitate the preparation of historical datasets for the LULC change detection and present an object-oriented joint classification scheme for multi-source datasets to accurately map the spatio-temporal changes. Our approach minimized the amount of manual digitizing required for the boundary delineation of LULC classes from historical geospatial data. Also, our quantitative analysis of LULC maps indicates diverging developments for the selected locations in the long period of 162 years. We observed rural depopulation and gradual afforestation in Aksu; whereas, agricultural land abandonment and deforestation in Kestel.

SUPER-RESOLUTION RESEARCH ON REMOTE SENSING IMAGES IN THE MEGACITY BASED ON IMPROVED SRGAN

Abstract. Remote sensing images of Earth observation with high spatial resolution and high temporal resolution are critical for the application of remote sensing technology in Megacities.With the development of Smart City,more demands which are still difficult to be perfectly satisfied on the spatial resolution and temporal resolution of remote sensing images have been put forward.This paper studies the use of SRGAN which means Super-Resolution using a Generative Adversarial Network (a network structure that uses the loss function considering the perceptual loss and the adversarial loss to improve the spatial resolution of remote sensing images) for super-resolution reconstruction of single remote sensing image.It is able to enhance the spatial resolution of remote sensing images and improve the depth and breadth of remote sensing images.We adjust the reasonable parameters and network structure for our research by analysing the SRGAN in the network architecture, the perceptual loss and the adversarial loss.A super-resolution model is obtained by training with aerial photogrammetry images whose spatial resolution are 0.1 meter in Shanghai.We find the improved SRGAN has a good performance in in remote sensing image super-resolution by comparing the super-resoved images with real high-resolution images in visual perception, spatial position mapping accuracy and chromaticity spatial information. In addition, it is proved that the trained model is also effective to deal with Worldview-2 and SuperView-1 satellite images whose spatial resolution are 0.5 m. Our research shows that our method which can effectively realize the super-resolution of remote sensing images has great potential in the application of remote sensing technology such as urban mapping and changes monitoring.

Optimum Feature and Classifier Selection for Accurate Urban Land Use/Cover Mapping from Very High Resolution Satellite Imagery

Feature selection to reduce redundancies for efficient classification is necessary but usually time consuming and challenging. This paper proposed a comprehensive analysis for optimum feature selection and the most efficient classifier for accurate urban area mapping. To this end, 136 multiscale textural features alongside a panchromatic band were initially extracted from WorldView-2, GeoEye-3, and QuickBird satellite images. The wrapper-based and filter-based feature selection were implemented to optimally select the best ten percent of the primary features from the initial feature set. Then, machine leaning algorithms such as artificial neural network (ANN), support vector machine (SVM), and random forest (RF) classifiers were utilized to evaluate the efficiency of these selected features and select the most efficient classifier. The achieved optimum feature set was validated using two other images of WorldView-3 and Pleiades. The experiments revealed that RF, particle swarm optimization (PSO), and neighborhood component analysis (NCA) resulted in the most efficient classifier and wrapper-based and filter-based methods, respectively. While ANN and SVM’s process time depended on the number of input features, RF was significantly resistant to the criterion. Dissimilarity, contrast, and correlation features played the greatest contributing role in the classification performance among the textural features used in this study. These trials showed that the feature number could be reduced optimally to 14 from 137; these optimally selected features, alongside the RF classifier, can produce an F1-measure of about 0.90 for different images from five very high resolution satellite sensors for various urban geographical landscapes. These results successfully achieve our goal of assisting users by eliminating the task of optimal feature selection and classifier, thereby increasing the efficiency of urban land use/cover classification from very high resolution images. This optimal feature selection can also significantly reduce the high computational load of the feature-engineering phase in the machine and deep learning approaches.

DOCSNet: a dual-output and cross-scale strategy for pan-sharpening

ABSTRACT Pan-sharpening aims to obtain a multi-spectral image of high resolution from inputs of a high spatial resolution panchromatic image and a low spatial resolution multi-spectral image. In recent years, pan-sharpening methods based on supervised learning have achieved superior performance over traditional methods. However, all these supervised pan-sharpening methods rest upon the assumption that performance of model trained on a coarse scale can generalize well on a finer one, which is not always the case. To address this problem, we propose a novel dual-output and cross-scale learning strategy DOCSNet for pan-sharpening. DOCSNet consists of two sub-networks, ReducedNet1 and FullNet2, which are both adapted from simple three convolutional layers and progressively cascaded. ReducedNet1 is first trained on the reduced-scale training set, its parameters are frozen, and then the whole network (fixed ReducedNet1 cascaded with FullNet2) adopts a cross-scale training strategy which involves simultaneously reduced and full resolution training samples. Each sub-network has an output terminal for reduced-scale and target-scale results, respectively. To the best of our knowledge, this is the first attempt to introduce a dual-output architecture to pan-sharpening framework. Extensive experiments on GaoFen-2 and WorldView-3 satellite images demonstrate that DOCSNet outperforms other state-of-the-art pan-sharpening methods in terms of qualitative visual effects and quantitative metrics evaluations.

Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images

Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images

EVALUATION OF EFFECTIVENESS OF PATCH BASED IMAGE CLASSIFICATION TECHNIQUE USING HIGH RESOLUTION WORLDVIEW-2 IMAGE

Abstract. The aim of the current study was to evaluate the performance of patch-based classification technique in land use/land cover classification and to investigate the effect of patch size in thematic map accuracy. To reach desired goal, recently proposed ensemble learning classifiers (i.e., XGBoost and CatBoost) were utilized to classify produced image patches obtained from high-resolution WorldView-2 (WV-2) satellite image. . In order to analyse the effect of varying patch size on classification accuracy, three different window sizes (i.e., 3 × 3, 7 × 7 and 11 × 11) were applied to WV-2 imagery for extracting image patches. Constructed image patches were classified using XGBoost and CatBoost ensemble learning classifiers and thematic maps were constructed for varying patch sizes. Results showed that while XGBoost and CatBoost showed similar classification performances for varying patch size and the estimated highest overall accuracy were %68, %82 and %92 for 11x11, 7 × 7 and 11 × 11 patch sizes, respectively. These findings confirmed that defining class boundaries on the high-resolution image using smaller patches increases the accuracy of thematic maps. In addition, results of patch-based classification were compared the results of LULC maps produced by same classifiers using pixel-based classification method. Overall accuracy of pixel-by-pixel classification of WV-2 image reached to about %94. Furthermore, CatBoost showed superior classification performance in all time compared to XGBoost. All in all, pixel-based CatBoost was found to be more successful in LULC mapping of fine resolution image.

Remote Sensing for Property Valuation: A Data Source Comparison in Support of Fair Land Taxation in Rwanda

Remotely sensed data is increasingly applied across many domains, including fit-for-purpose land administration (FFPLA), where the focus is on fast, affordable, and accurate property information collection. Property valuation, as one of the main functions of land administration systems, is influenced by locational, physical, legal, and economic factors. Despite the importance of property valuation to economic development, there are often no standardized rules or strict data requirements for property valuation for taxation in developing contexts, such as Rwanda. This study aims at assessing different remote sensing data in support of developing a new approach for property valuation for taxation in Rwanda; one that aligns with the FFPLA philosophy. Three different remote sensing technologies, (i) aerial images acquired with a digital camera, (ii) WorldView2 satellite images, and (iii) unmanned aerial vehicle (UAV) images obtained with a DJI Phantom 2 Vision Plus quadcopter, are compared and analyzed in terms of their fitness to fulfil the requirements for valuation for taxation purposes. Quantitative and qualitative methods are applied for the comparative analysis. Prior to the field visit, the fundamental concepts of property valuation for taxation and remote sensing were reviewed. In the field, reference data using high precision GNSS (Leica) was collected and used for quantitative assessment. Primary data was further collected via semi-structured interviews and focus group discussions. The results show that UAVs have the highest potential for collecting data to support property valuation for taxation. The main reasons are the prime need for accurate-enough and up-to-date information. The comparison of the different remote sensing techniques and the provided new approach can support land valuers and professionals in the field in bottom-up activities following the FFPLA principles and maintaining the temporal quality of data needed for fair taxation.

Deep Learning for Effective Refugee Tent Extraction Near Syria–Jordan Border

Rukban is a desert area crossing the border between Syria and Jordan, and thousands of Syrian refugees fled into this area since the Syrian civil war in 2014. In the past few years, the number of refugee shelters for the forcibly displaced Syrian refugees in this area has increased rapidly. Estimating the location and number of refugee tents has become a key factor to maintain the sustainability of the refugee shelter camps. Manually counting the shelters is labor-intensive and sometimes prohibitive given the large quantities. In addition, these shelters/tents are usually small in size, irregular in shape, and sparsely distributed in a very large area and could be easily missed by the traditional image-analysis techniques, making the image-based approaches also challenging. In this letter, we proposed a deep fully convolutional neural network (FCN) model to extract automatically the refugee shelters/tents in the worldview-2 (WV-2) satellite images. In addition, we transferred knowledge in the pretrained VGG-16 model to improve the detection accuracy and network training convergence. We compared the proposed approach with the traditional spectral angle mapper (SAM) method, deep convolutional neural network (CNN) models, and the mask Region-based CNN (R-CNN) model. The experimental results show that the FCN model improved the overall accuracy by 4.49%, 3.54%, and 0.88% compared with the CNNs, SAM, and mask R-CNN models, and improved the precision by 34.61%, 41.99%, and 11.87%, respectively.