WorldView-2 Satellite Research Articles

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.

Urban footprint extraction derived from worldview-2 satellite imagery by random forest and k-nearest neighbours algorithm

High-resolution spatial data regarding the distribution of urban areas is fundamental concerning regional spatial planning and monitoring the development of built-up areas. Many researchers have extracted urban footprints using low to medium-resolution satellite imagery. For applications on a global and regional scale, low to medium image resolution are suitable. Nevertheless, higher image resolution is required on a local scale, down to a small urban area level. This study objective to mapping the built-up land and examine the accuracy of 2 machine learning algorithms. This investigation employs a novel approach that combines the utilization of remote sensing technology with the implementation of machine learning algorithms. We use Random Forest (RF) and K-Nearest Neighbours (KNN) machine learning algorithms. This study used a high-resolution (0.5 meter) satellite image derived formWorldView-2. We only used three visible channels (Red-Green-Blue) with a 450 – 690 nm wavelength. Integrating remote sensing and machine learning can adequately investigate the urban footprint area. Based on this research, the RF better than KNN algorithm. It is proven by the confidence iteration value and the overall accuracy of the RF and KNN algorithms, i.e., 73.32%, 71.99%, 82.08%, and 77.89% respectively. Based on WorldView-2 imagery acquired in 2015, the proportion of urban footprint is still lower than the green area with 41.75%: 58.24%, especially in the centre of the capital city of Bali Province. Such conditions are undoubtedly different in other urban areas in Bali. Even one city area, e.g., West Denpasar, which almost the entire area is dominated by the urban footprint area. Such conditions are a particular concern for the local government in managing future spatial planning regulations. It is recommended that the proportion of green open space remains a priority so that there are no environmental problems in urban areas (e.g., air pollution, flooding due to runoff problems, etc.).

Study of the evolution of oil spill sites based on high-resolution satellite images: the case of the Samotlor field

A methodology for visual interpretation of accidental oil spills using satellite images from the WorldView-3 satellite equipped with short-wave infrared (SWIR) channels is proposed, with verification using multi-temporal very-high-resolution images in the Google Earth system. The analysis of the images of four large oil spills in the southeastern part of the Samotlor field made it possible to study the degradation changes in different types of vegetation and the processes of its self-recovery for 2017–2022. The comparison of the results of image analysis with the data from field studies reveals their good agreement and the need for further development of methods for remote monitoring of oil spills using the SWIR range.

Detection and mapping of artillery craters with very high spatial resolution satellite imagery and deep learning

Unexploded munitions are some of the most enduring remnants of conflicts around the world. Their effects on the economy, health, environment, and post-conflict rehabilitation are long reaching and devastating for the areas they plague. With the advancements in very high spatial resolution (VHR) satellite multispectral imaging at sub-meter resolution, it becomes possible to detect object attributes at the scale of individual impacts (craters) of heavy weapon shelling. Manual identification and delineation of artillery craters in satellite imagery is time and resource consuming, especially when large territories and volumes of VHR data are considered. Therefore, automatic image processing methods should be explored. Here, we evaluate the application of a deep learning approach for identifying and mapping artillery craters in agricultural fields in Eastern Ukraine during the onset of armed conflict in 2014. The model was applied to pansharpened multispectral VHR imagery acquired by the WorldView-2 satellite at 0.5-m spatial resolution. The model can detect artillery craters with producer's accuracy (PA) (or recall) of 0.671 and user's accuracy (UA) (or precision) of 0.392 in terms of crater area and shape, and PA of 0.559 and UA of 0.427 in terms of binary crater identification. The model's performance is dependent on crater size. Reliability of crater detection and mapping improves as the size of craters increases. For example, for craters larger than 60 m2 PA is 0.803 and UA is 0.449 (per-pixel), and PA is 0.891 and UA is 0.721 (per-object). Overall, the model prioritizes PA over UA, i.e., omission error over commission error, and is better at detecting craters than their shapes. We applied the trained model to a separate, 858 km2 subregion of Donetsk oblast to automatically estimate and map the locations, number and area of artillery craters. Our estimates revealed over 22,000 craters in the subregion, which occupy an area of 1.2 km2, or 0.14% of the region, primarily in agricultural fields. The availability of such crater maps is extremely valuable within demining and chemical decontamination efforts and can assist in assessing the impact of warfare on agriculture and the environment. We outline the current limitations of the proposed approach and avenues for further research for improving artillery crater detection and mapping.

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.

The Detection of Nitrogen Saturation for Real-Time Fertilization Management within a Grassland Ecosystem

Unfettered agricultural activities have severely degraded vast areas of grasslands over the last decade. To rehabilitate and restore the productivity in affected grasslands, rangeland management practices still institute vast nitrogen-based fertilization regimes. However, excessive fertilization can often have damaging environmental effects. Over-fertilization can lead to nitrogen saturation. Although early indicators of nitrogen saturation have been documented, research detailing the near-real-time nitrogen saturation status of grasslands is required to better facilitate management protocols and optimize biomass production within degraded grasslands. Hence, the aim of this study was to discriminate nitrogen-saturated tropical grasses grown under a diverse fertilization treatment trial, using Worldview-3 satellite imagery and decision tree techniques. To accomplish this, nitrogen-saturated plots were first identified through specific physiological-based criteria. Thereafter, Worldview-3 satellite imagery (400–1040 nm) and decision tree techniques were applied to discriminate between nitrogen-saturated and -unsaturated grassland plots. The results showed net nitrate (NO3−-N) concentrations and net pH levels to be significantly different (α = 0.05) between saturated and non-saturated plots. Moreover, the random forest model (overall accuracy of 91%) demonstrated a greater ability to classify saturated plots as opposed to the classification and regression tree method (overall accuracy of 79%). The most important variables for classifying saturated plots were identified as: the Red-Edge (705–745 nm), Coastal (400–450 nm), Near-Infrared 3 (838–950 nm), Soil-Adjusted Vegetation Index (SAVI) and the Normalized Difference Vegetation Index 3 (NDVI3). These results provide a framework to assist rangeland managers in identifying grasslands within the initial stages of nitrogen saturation. This will enable fertilization treatments to be adjusted in near-real-time according to ecosystem demand and thereby maintain the health and longevity of Southern African grasslands.

Mapping invasive alien plant species with very high spatial resolution and multi-date satellite imagery using object-based and machine learning techniques: A comparative study

ABSTRACT Invasive alien plant species (IAPS) have negative impacts on ecosystems, including the loss of biodiversity and the alteration of ecosystem functions. The strategy for mitigating these impacts requires knowledge of these species’ spatial distribution and level of infestation. In situ inventories or aerial photo interpretation can be used to collect these data but they are labor-intensive, time-consuming, and incomplete, especially when dealing with large or inaccessible areas. Remote sensing may be an effective method of mapping IAPS for a better management strategy. Several studies using remote sensing to map IAPS have focused on single species detection and were conducted in relatively homogeneous natural environments, while other common, more heterogeneous environments, such as urban areas, are often invaded by multiple IAPS, posing management challenges. The main objective of this study was to develop a mapping method for three major IAPS observed in the urban agglomeration of Quebec City (Canada), namely Japanese knotweed (Fallopia japonica); giant hogweed (Heracleum mantegazzianum); and phragmites (Phragmites australis). Mono-date and multi-date classification approaches were used with WorldView-3 and SPOT-7 satellite imagery, acquired in the summer of 2020 and in the autumn of 2019, respectively. To estimate presence probability, object-based image analysis (OBIA) and nonparametric classifiers such as Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) were used. Overall, multi-date classification using WorldView-3 and SPOT-7 images produced the best results, with a Kappa coefficient of 0.85 and an overall accuracy of 91% using RF. For XGBoost, the Kappa coefficient was 0.81 with an overall accuracy of 89%, whereas the Kappa coefficient and overall accuracy were 0.80 and 88% for SVM classifier, respectively. Individual class performances based on F1-score revealed that Japanese knotweed had the highest maximum value (0.95), followed by giant hogweed (0.91), and phragmites (0.87). These results confirmed the potential of remote sensing to accurately map and simultaneously monitor the main IAPS in a heterogeneous urban environment using a multi-date approach. Although the approach is limited by image and reference data availability, it provides new tools to managers for IAPS invasion control.

Pecora 22: Remote Sensing for Freshwater and Marine Environments

Pecora 22: Remote Sensing for Freshwater and Marine Environments

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.

Integrating UAV-Derived Information and WorldView-3 Imagery for Mapping Wetland Plants in the Old Woman Creek Estuary, USA

The classification of wetland plants using unmanned aerial vehicle (UAV) and satellite synergies has received increasing attention in recent years. In this study, UAV-derived training and validation data and WorldView-3 satellite imagery are integrated in the classification of five dominant wetland plants in the Old Woman Creek (OWC) estuary, USA. Several classifiers are explored: (1) pixel-based methods: maximum likelihood (ML), support vector machine (SVM), and neural network (NN), and (2) object-based methods: Naïve Bayes (NB), support vector machine (SVM), and k-nearest neighbors (k-NN). The study evaluates the performance of the classifiers for different image feature combinations such as single bands, vegetation indices, principal components (PCs), and texture information. The results showed that all classifiers reached high overall accuracy (>85%). Pixel-based SVM and object-based NB exhibited the best performance with overall accuracies of 93.76% and 93.30%, respectively. Insignificantly lower overall accuracy was achieved with ML (92.29), followed by NN (90.95) and object-oriented SVM (90.61). The k-NN method showed the lowest (but still high) accuracy of 86.74%. All classifiers except for the pixel-based SVM required additional input features. The pixel-based SVM achieved low errors of commission and omission, and unlike the other classifiers, exhibited low variability and low sensitivity to additional image features. Our study shows the efficacy of combining very high spatial resolution UAV-derived information and the super spectral observation capabilities of WorldView-3 in machine learning for mapping wetland vegetation.

Aplikasi Teknologi Drone Sebagai Pelengkap Data Survei Lapang Untuk Pemetaan Ekosistem Terumbu Karang Menggunakan Citra Worldview-2

Coral reefs are one of the important ecosystems that need data inventory in order to manage marine resources both spatially and temporally. Remote sensing with drone technology is one of the vehicles for collecting data related to coral reef ecosystems in real time. Along with the times, drones are widely used in research both in terrestrial and in coastal areas. This research was conducted on December 4 – 10, 2018 in the Karang Lebar, Seribu Islands, Jakarta. The purpose of this research was to explored the ability of drones as a vehicle to complement field survey data for coral reef mapping. In addition, conducting a pixel-based analysis for coral reef classification based on WorldView-2 satellite imagery using field survey data and additional data from drone data. Based on the results of the study, information was obtained that drone imagery can help visual interpretation in detecting coral reefs. Thus, field survey data that are not covered in the research area can be assisted by the use of drones as a complementary vehicle for field survey data. The coral reef classification process using WorldView-2 imagery can be mapped well. Drone imagery has proven to be an alternative in field data collection as a training area in identifying coral reef objects, such as with massive coral lifeforms that can be clearly seen from drone images. It's just that visual interpretation is limited because of the water column, making it difficult to identify objects.

Eutrophic Status Assessment Based on Very High-Resolution Satellite Imagery in the Coastline Environment of Korea

Anthropoid activities are severely altering natural land cover and growing the transport of soil, organic and inorganic compounds, nutrients, toxic chemicals, and other pollutants to the water ecosystem. The eutrophication of the coastal water environment is one of the furthermost bitter consequences of human activities. In this research, we have used three different satellite images for efficient land-use land-cover (LULC) classification, comparison, and further coastal water quality assessment over the coastal zone of the Boseong County of South Korea. The results of LULC classification showed that Landsat-8, Sentinel-2, and WorldView-3 gave an overall accuracy of about 74%, 82%, and 96% with Kappa coefficient of 0.71, 0.78, and 0.91, respectively. By comparing, LULC accuracies and kappa coefficient, the very high-resolution Worldview-3 satellite imagery is considered one of the best-suited satellite imageries for water quality assessment. The study used recently developed algorithms for the calculation of the transparency of Secchi depth, concentration of Chlorophyll-a, Total Phosphorus, and Total Nitrogen; whereas the eutrophication status of the coastal water has been identified using the Carlson Trophic State Index (CTSI) method. The result show that the medium state of eutrophication occurred nearby agricultural regions and urban settlements. Overall, trophic status of the coastal water is ranged from 61.56 to 74.37 with a mean value of 65.63 (CTSI) and placed under the medium eutrophic state. The study analysed that the nutrient entrance from the surrounding land cover is high and needs proper water treatment before releasing into a coastal ecosystem. Hence, these investigations will assist the various local and international agencies in improving the reliability of the monitoring of eutrophication state, dynamics, and potential impacts.

A Hybrid Algorithm for Urban LULC Change Detection for Building Smart-city by Using WorldView Images

Technological advancement in smart cities can have adverse effects on the environment. Timely monitoring of smart cities to preserve environmental sustainability is a thrust area of research. It can be done by using change detection with multi-temporal satellite data. The success of these methods solely depends on the calibre of the backend image segmentation and Land-use Land-cover classification technique. The limitation of using cutting-edge classification algorithms is the availability of a proper dataset and identification of the edge structure of different LULC classes. In contrast, a segmentation algorithm cannot detect LULC classes automatically. In this research, we eliminated these shortcomings by considering a hybrid approach. We proposed a multi-class Support Vector Machine (SVM) and ISODATA-embedded large-scale change detection method. This method can automatically segment, detect, and perform LULC change analysis. We have considered the multi-sensor dataset of Barasat, West Bengal, India, obtained from the WorldView satellite sensor for the experimental study. The proposed method is validated concerning three different cutting-edge methods.

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.

A general deep learning based framework for 3D reconstruction from multi-view stereo satellite images

In this paper, we propose a general deep learning based framework, named Sat-MVSF, to perform three-dimensional (3D) reconstruction of the Earth’s surface from multi-view optical satellite images. The framework is a complete processing pipeline, including pre-processing, a multi-view stereo (MVS) network for satellite imagery (Sat-MVSNet), and post-processing. The pre-processing handles the geometric and radiometric configuration of the multi-view images and their cropping. The cropped multi-view patches are then fed into Sat-MVSNet, which includes deep feature extraction, rational polynomial camera (RPC) warping, pyramid cost volume construction, regularization, and regression, to obtain the height maps. The error matches are then filtered out and a digital surface model (DSM) is generated in the post-processing. Considering the complexity and diversity of real-world scenes, we also introduce a self-refinement strategy that does not require any ground-truth labels to enhance the performance and robustness of the Sat-MVSF framework. We comprehensively compare the proposed framework with popular commercial software and open-source methods, to demonstrate the potential of the proposed deep learning framework. On the WHU-TLC dataset, where the images are captured with a three-line camera (TLC), the proposed framework outperforms all the other solutions in terms of reconstruction fineness, and also outperforms most of the other methods in terms of efficiency. On the challenging MVS3D dataset, where the images are captured by the WorldView-3 satellite at different times and seasons, the proposed framework also exceeds the existing methods when using the model pretrained on aerial images and the introduced self-refinement strategy, demonstrating a high generalization ability. We also note that the lack of training samples hinders research in this field, and the availability of more high-quality open-source training data will greatly accelerate the research into deep learning based MVS satellite image reconstruction. The code will be available at https://gpcv.whu.edu.cn/data.

Mapping Dwellings in IDP/Refugee Settlements Using Deep Learning

The improvement in computer vision, sensor quality, and remote sensing data availability makes satellite imagery increasingly useful for studying human settlements. Several challenges remain to be overcome for some types of settlements, particularly for internally displaced populations (IDPs) and refugee camps. Refugee-dwelling footprints and detailed information derived from satellite imagery are critical for a variety of applications, including humanitarian aid during disasters or conflicts. Nevertheless, extracting dwellings remains difficult due to their differing sizes, shapes, and location variations. In this study, we use U-Net and residual U-Net to deal with dwelling classification in a refugee camp in northern Cameroon, Africa. Specifically, two semantic segmentation networks are adapted and applied. A limited number of randomly divided sample patches is used to train and test the networks based on a single image of the WorldView-3 satellite. Our accuracy assessment was conducted using four different dwelling categories for classification purposes, using metrics such as Precision, Recall, F1, and Kappa coefficient. As a result, F1 ranges from 81% to over 99% and approximately 88.1% to 99.5% based on the U-Net and the residual U-Net, respectively.

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.