The reliable quantification of the global built-up surface distribution and its dynamics using Earth Observation data is a fundamental task for many scientific and policy-related applications. The emergence of various global geospatial datasets on human settlements derived from high-resolution Earth Observation data allows practitioners to choose from a variety of global datasets, for which detailed knowledge on data accuracy and semantics is crucial. Herein, we employ novel, quasi-global building footprint data as reference data and develop a framework to assess the accuracy of global EO-derived human settlement data, such as the Global Human Settlement Layer (GHSL), and others. We present preliminary results of these accuracy assessments, at different analytical scales and stratified across different dimensions. Our analyses reveal that for continuous, sub-pixel built-up surface estimation, the GHSL outperforms other global settlement-related datasets under test and provides a reliable baseline for geospatial analyses supporting scientific research and decision making.

Abstract Spatially consistent and up-to-date maps of human settlements are crucial for addressing policies related to urbanization and sustainability, especially in the era of an increasingly urbanized world. The availability of open and free Sentinel-2 data of the Copernicus Earth Observation program offers a new opportunity for wall-to-wall mapping of human settlements at a global scale. This paper presents a deep-learning-based framework for a fully automated extraction of built-up areas at a spatial resolution of 10 m from a global composite of Sentinel-2 imagery. A multi-neuro modeling methodology building on a simple Convolution Neural Networks architecture for pixel-wise image classification of built-up areas is developed. The core features of the proposed model are the image patch of size 5 × 5 pixels adequate for describing built-up areas from Sentinel-2 imagery and the lightweight topology with a total number of 1,448,578 trainable parameters and 4 2D convolutional layers and 2 flattened layers. The deployment of the model on the global Sentinel-2 image composite provides the most detailed and complete map reporting about built-up areas for reference year 2018. The validation of the results with an independent reference dataset of building footprints covering 277 sites across the world establishes the reliability of the built-up layer produced by the proposed framework and the model robustness. The results of this study contribute to cutting-edge research in the field of automated built-up areas mapping from remote sensing data and establish a new reference layer for the analysis of the spatial distribution of human settlements across the rural–urban continuum.

This letter introduces the new European Settlement Map (ESM) production workflow, presents some indicatory results, and discusses the validation process. Unlike the previous ESM versions, the built-up (BU) extraction is realized through supervised learning (not only by means of image filtering and processing techniques) based on textural and morphological features. Input data are the Copernicus very-high-resolution image collection for the reference year 2015 coming from a variety of sensors. The workflow is fully automated, and it does not include any postprocessing. For the first time, a new layer containing nonresidential buildings was derived by using only remote sensing imagery and training data. The produced BU map is delivered at 2-m-pixel resolution (level-1 layer), while the residential/nonresidential layer (level 2) is delivered at 10-m spatial resolution. More than 46 000 scenes were processed, and around 6 million km2of the European territory was mapped. The workflow was executed on the JRC Big Data platform. The validation showed a balanced accuracy of 0.81 and 0.91 for level 1 and 2 layers, respectively, and 0.71 for only the nonresidential layer.

This paper presents a processing chain for handling big volume of remotely sensing data for generating wide extent mosaics. More specifically, the data under consideration are level-1 ground range detected Sentinel-1 products with dual polarisation (VV+VH or HH+HV). Two approaches for a) distribution discretization accompanied by false color composition and b) image rendering and mosaicking are proposed. While these two components are necessary constituents of the presented mosaicking workflow, they can operate independently of each other. The design of the processing chain satisfies three objectives: i) contrasting derivative products of the input Sentinel-1 imagery such as the Global Human Settlement Layer, ii) adapting on a high-throughput computing system for fast execution, and iii) allowing potential extensions to more complex applications such as the image classification. Fast processing, process automation, incremental adjustment and information distinction are the main advantages of the proposed method. Elaboration and focus on these features are carried out during the presentation of the results.

The Global Human Settlement Layer (GHSL) produces new global spatial information, evidence-based analytics and knowledge describing the human presence on the planet based mainly on two quantitative factors: i) the spatial distribution (density) of built-up structures and ii) the spatial distribution (density) of resident people. Both factors are observed in the long-term temporal domain and per uniform surface units in order to support trends and indicators for monitoring the implementation of international framework agreements. The GHSL uses various input data including global, multi-temporal archives of fine-scale satellite imagery, census data, and volunteered geographic information. In this paper, the main principles driving the design and the implementation of the GHSL information production system are outlined, together with a summary of the key applications and use scenarios.

In this paper we examine the impact of the growing urbanization of Dar es Salaam, Tanzania, on the forest areas around the city. Since 1990 the city has seen an annual population growth rate of over 4%. We document the expansion of the city over the last 30 using the Global Human Settlement Layers, derived from the global Landsat archive. At the same time we show the depletion, of the surrounding forests that has occurred to meet the growing demand for agricultural land, fuel wood and construction material over the same period. The impact on these forests as a result of the demand from an expanding urban conglomeration is higher than would be expected from a dispersed population increase. The results show that to satisfy the demands of the city and of its expanding suburbs, forests from further afield are being depleted and that protected areas nearer the city are being compromised.

The growth of the built environment is a global environmental change processes that can be measured and monitored with Earth Observation. That growth is expected to continue as populations continue to both increase and urbanize. The Global Human Settlement Layer (GHSL) project was set up to measure and monitor the global built up environment and its changes [1]. The GHSL layers presented herein are derived by processing the global archive of Landsat imagery dating back to 1975. GHSL from Landsat include four global built up information layers corresponding to epochs: 1975, 1990, 2000 and 2014 [2]. The geo-information generated is used in a wide variety of applications that include the generation of urbanization statistics, to quantify exposure to natural hazards for disaster risk and early warning models, to derive global fine scale population density grids, and to generate indicators to monitor targets for main international framework agreements.

This paper shows how remote sensing derived information about the human and physical exposure can be used to support disaster alert systems. The human and physical exposures are calculated from LandScan and GHSL datasets, respectively. In this approach, a multiscale alert system relies on Web services that offer information about the amount of population and infrastructure affected by a given hazard. Four natural disaster scenarios have been selected to cover different spatial scales and disaster types.

Detailed geoinformation on settlements are required for disaster risk analysis and crisis management, yet are only readily available for specific areas, varying widely in quality and characteristics. Remote sensing can contribute to fill this gap. The Global Human Settlement Layer (GHSL) project provides detailed data on the distribution and densities of built-up for continent-wide expanses, in a consistent way. This paper illustrates the application of GHSL-derived geoinformation in the assessment of physical and human exposure to floods at the local level. Results show that GHSL refines on existing information and contributes to improve analyses of exposure and risk of natural disasters.

Available global population grids suffer from limitations that constrain their usability. The Global Human Settlement Layer (GHSL) may benefit population disaggregation and mapping. We test the integration of the GHSL built-up grid and the Gridded Population of the World (GPW) in order to refine the mapping of population distribution in Syria, for the year 2000, greatly improving depiction of population distribution and density. Preliminary results indicate that GHSL is a good proxy for population disaggregation.

The paper addresses built up information extraction from high resolution imagery from two satellites, ZY-1 02C and SPOT-5. The testing is part of a larger experiment that explores spectral, textural and morphological satellite image properties aiming to extract built up information for global built up mapping and characterization. In this work we test SPOT-5 and ZY-1 02C satellites for textural properties associated to built-up. The work is exploratory in nature. We compute image textures using a ”built-up presence index (Pantex)” algorithm. We then compare the texture values with a reference built-up map derived from building footprints map by computing the Receiver Operative Characteristics (ROC). We processed four bands: ZY-HR Panchromatic, ZY Panchromatic, and two “brightness” bands derived from the ZY Pan-sharpened, and SPOT Pan-sharpened. Pan-sharpened products combine both the panchromatic and the multispectral imagery. For each dataset we use two texture windows for a total of eight tests. The study is conducted on imagery covering the city of Firenze, Italy. The landscape is characterized by dense city centres as well as rural scattered settlement. The area is deemed suitable to benchmarking imagery for built up information related to human settlements of different densities. The test shows that the information from SPOT and ZY are generating similar result. However, spatial resolution of panchromatic bands show to have great importance over other factors in extracting built up information.

This paper describes the methodology and the results of a comprehensive automatic image classification task aiming to map the European settlements using 2.5m-resolution input data. The processing approach is consistent with the Global Human Settlement Layer (GHSL) [1]; certain adjustments were driven by the specific input data characteristics and the specific application needs. In the study discussed here, a total of 2,275 SPOT-5 3-band pan-sharpened images were processed. The main output is a seamless 10m-resolution raster mosaic. Each pixel value expresses the proportion of the pixel area covered by buildings. Complementary information about the open spaces between buildings and the proportion of vegetation is also produced at the same spatial resolution.

An interscale learning paradigm for global HR/VHR image information extraction is presented. The paradigm relies on the information matching between a priori global knowledge and features derived from high resolution imagery to perform adaptive high resolution land classification. Unlike traditional machine learning techniques, this strategy avoids the costly collection of local training datasets and the local parameter tuning and it enables the full automation of the information extraction process.

A new built-up presence index based on the density of corners is presented. Corners are detected by multi scale Harris detector based on Differential Morphological Decompositions before being aggregated in a density of corners. Experiments are conducted with several high resolution panchromatic images and the density of corners is shown to be highly correlated to the PanTex built-up index [1].

Remote sensing is an effective tool in urban extent mapping and monitoring. In this study, a procedure to detect urban expansion is presented using SPOT5 panchromatic image with 2.5m resolution. First of all, the urban extents of different images are extracted with a PANTEX methodology, which use the anisotropic rotation-invariant textural grey-level co-occurrence measures as the presence of built-up areas. The change detection is performed on the two built-up index images using principal component analysis technique. Finally, the accuracy of this procedure is assessed with visual analysis results. The method shows good performance according to the overall accuracy of 91.18% (Kappa coefficient=0.8719).

Roofless buildings are encountered in case of conflicts and disasters as well as construction sites. A methodology for characterizing and counting roofless buildings in very high resolution optical images is presented. Using morphological transform to extract specific image components, the proposed method spatially aggregates them in a fuzzy logic framework. The result is a map of roofless building membership. This membership map is then used with partial ground truth to estimate the total number of roofless buildings. Finally, the methods are validated with a WorldView panchromatic image, where the membership map and the counting estimate show good accuracies.

Differential area profiles (DAPs) are point-based multiscale descriptors used in pattern analysis and image segmentation. They are defined through sets of size-based connected morphological filters that constitute a joint area opening top-hat and area closing bottom-hat scale-space of the input image. The work presented in this paper explores the properties of this image decomposition through sets of area zones. An area zone defines a single plane of the DAP vector field and contains all the peak components of the input image, whose size is between the zone's attribute extrema. Area zones can be computed efficiently from hierarchical image representation structures, in a way similar to regular attribute filters. Operations on the DAP vector field can then be computed without the need for exporting it first, and an example with the leveling-like convex/concave segmentation scheme is given. This is referred to as the one-pass method and it is demonstrated on the Max-Tree structure. Its computational performance is tested and compared against conventional means for computing differential profiles, relying on iterative application of area openings and closings. Applications making use of the area zone decomposition are demonstrated in problems related to remote sensing and medical image analysis.

Very High Resolution (VHR) satellite images are products which are very useful for assessing humanitarian situations following a disaster or a crisis. When disaster or conflict hits, generally several square kilometers on Earth surface are involved. Having a high resolution and an extended surface, the scenes, from which the information is extracted, become huge in the number of pixels. Built-up structures are the first visible objects from these images which give information about the situation. In this paper, an interactive image mining paradigm is presented for detecting structures of interest in gigapixel images. The proposed approach is tested for refugee tents detection in submetric panchromatic image.

A new unsupervised change detection method for modeling nonlinear temporal dependences based on local information is proposed. A theoretical analysis is presented, demonstrating how to derive optimal parameters for automating the method. It is then validated on both simulated data and very high resolution remote sensing imagery. The results show a clear improvement in change detection using the proposed method compared to other state-of-the-art change detection techniques.

In order to describe, to extract image information content, segmentation is a well-known approach to represent the information in terms of objects. Image segmentation is a common image processing technique aiming at disintegrating an image into a partition of its support. Hierarchical of fuzzy segmentation are extension of segmentation definition, in order to provide a covering of the image support with overlapping segments. In this paper, we propose a novel approach for breaking up an image into multi-scale overlapping objects. The image is decomposed by granulometry or differential morphological pyramid, resulting in a discrete scale-space representation. Then, the scale-space transform is segmented by a region based method. Projecting the obtained scale-space partition into space constitutes the disintegrated image representation, which enables a multi-scale object based image description.

Recent experience in using meter and sub-meter satellite images in support to crisis management is discussed in this paper. Technical challenges and conceptual gaps in automatic information extraction are described from a perspective of the Joint Research Center's experience in crisis management. Some methodological propositions are given to cope with these challenges, which were revealed in experiments realized in various crisis scenarios.

The results shown in this paper highlights the usefulness of a recently proposed index to extract hints of built-up areas in remotely sensed images. The novelty of this work is in the application of the approach to a very different data set than the one for which the index was originally developed, i.e. SAR instead of optical data. Due to the different approaches (active vs. passive sensors), wavelengths (optical vs. microwave) and distortion/noise effects (additive vs. speckle noise), it is valuable to find out the advantages and limits of the index results on these new data sets. Moreover, due to the different geometry of acquisition for radar sensors, two different implementations of the same index are considered and compared, adding insights on the suitability of slant-range vs. ground-range analysis of SAR data for built-up area recognition.

The problem of classification of high-resolution remotely sensed images from urban areas is addressed. Previous studies have shown the interest in exploiting the local geometrical information of each pixel to improve the classification. This is performed using the derivative morphological profile obtained with a granulometric approach using respectively opening and closing operators. We propose to replace this by a morphological alternated sequential filter, where the openings and the closings are applied alternately. The results and the robustness provided by the ASF are presented on IKONOS panchromatic data.

Classification of panchromatic high-resolution data from urban areas using morphological and neural approaches is investigated. The proposed approach is based on three steps. First, the composition of geodesic opening and closing operations of different sizes is used in order to build a differential morphological profile that records image structural information. Although, the original panchromatic image only has one data channel, the use of the composition operations will give many additional channels, which may contain redundancies. Therefore, feature extraction or feature selection is applied in the second step. Both discriminant analysis feature extraction and decision boundary feature extraction are investigated in the second step along with a simple feature selection based on picking the largest indexes of the differential morphological profiles. Third, a neural network is used to classify the features from the second step. The proposed approach is applied in experiments on high-resolution Indian Remote Sensing 1C (IRS-1C) and IKONOS remote sensing data from urban areas. In experiments, the proposed method performs well in terms of classification accuracies. It is seen that relatively few features are needed to achieve the same classification accuracies as in the original feature space.

Summary form only. Classification of panchromatic IKONOS data from an urban area in Reykjavik, Iceland is investigated. It is well known that conventional classification algorithms like the Gaussian maximum likelihood method are not appropriate for classification of high-resolution data from urban areas. Therefore, in the paper, an approach based on morphological pre-processing and neural networks is applied. Several types of morphological transformations were used, each based on compositions of morphological opening and closing transforms. Three data sets were created: A) Data 1: Normal morphological opening and closing operations were used. The size of the structural elements was determined as the size of a square structural element and a quadratic increment step was used. The processed image consisted of the original image, 15 opening channels and 15 closing channels (31 channels in total). The derivative of the morphological profile was also computed, resulting in 30 channels. B) Data 2: Open and closing by reconstruction was used with a linear increment step of 1. The size was the number of connected pixels (the area) of structures, and that was in contrast to Data 1, independent of the shape. The original image, 20 opening channels, and 20 closing channels were classified (41 channels in total). The derivative of the morphological profile was also computed and used in classification, resulting in 40 channels. C) Data 3: Same as Data 2, except, a linear increment step of 2 was used instead of an increment of 1. The classification of these different data sets showed interesting characteristics in classification.

By concentrating on the analysis of the spatial relationships between groups of pixels, mathematical morphology provides us with an image processing strategy complementary to those based on the analysis of the spectral signature of single pixels. A wide variety of morphological transformations are available for extracting structural information in spatial data. Accordingly, a stream of successful applications in geoscience and remote sensing have been reported since the mid-1980s as highlighted in a brief survey. However, recent advances in the theory of mathematical morphology still remain largely unexplored. We show in this paper that they can enhance methodologies for the processing and analysis of Earth observation data for tasks as diverse as filtering, simplification, directional segmentation and crest line extraction. We also address important issues overlooked in the past and concerning the applicability of a given morphological filter to Earth observation data. In particular, we point out that self-dual or even self-complementary filters are required in many applications to produce results independent of the local contrast of the searched image structures.

A new segmentation method based on the morphological characteristic of connected components in images is proposed. Theoretical definitions of morphological leveling and morphological spectrum are used in the formal definition of a morphological characteristic. In multiscale segmentation, this characteristic is formalized through the derivative of the morphological profile. Multiscale segmentation is particularly well suited for complex image scenes such as aerial or fine resolution satellite images, where very thin, enveloped and/or nested regions must be retained. The proposed method performs well in the presence of both low radiometric contrast and relatively low spatial resolution. Those factors may produce a textural effect, a border effect, and ambiguity in the object/background distinction. Segmentation examples for satellite images are given.

In the framework of the textural-based classification of very-high resolution satellite imagery for urban analysis applications, the paper presents an exploration of the interaction between textural window size and standard statistical classification output quality. In contrast to the common approach that assumes a generically decreasing accuracy function for increasing textural window size, a non-intuitive result of this work is the demonstration of the possibility of obtaining high classification performance with very wide-area textural windows. Another interesting result is the observation that small textural patches in the image can also be detected with relatively very large textural windows.