Skip to content

Satellites view the Earth as a whole – collecting data without regard to political boundaries. In an ever-changing and uncertain world, very high resolution (VHR) satellite imagery is fast becoming a common tool to predict future threats, monitor development outcomes and minimise risk at all levels of government. As such, policy makers now need to be provided with more information than ever before and usually this information is time critical.

Information derived from optical satellite imagery provides a whole new way of looking at the world. As well as tabled data, VHR imagery can provide a 3D overview of the state of the Earth and allows you to see the current situation in near-real-time, permitting optimised responses for the best possible outcome. It adds another level of detail that can serve numerous purposes and is an indispensable source of information gap filling.

Security Surveillance for Safer Borders

The power of VHR data lies in the detail. It can provide empirical answers to questions concerning multiple humanitarian and border security applications. Due to the resolution of the imagery, tents and cars can easily be identified from the sky allowing the movement of refugees to be monitored in addition to the mapping of displaced populations. The technology also provides more measured border security controls both at a domestic and international level. Oceans are large and ships are small however through the aid of satellite technology, policy makers knowledge of the entire ocean and not just coastal zones, can be significantly increased. The wide reach of the technology also means that no area of the ocean is unable to be captured. As a result, countries can reduce the number of illegal immigrants entering, reduce the death toll of human lives at seas and increase internal security within the country by preventing cross-border crime.

Agriculture Insights for Modern Frameworks

VHR imagery provides the opportunity for multispectral analysis to be conducted. With multispectral imagery, it is possible to extract additional information that the human eye fails to see. Too often the issue regarding the lack of basic information required for sustainable food security poses a threat to governments. Without up to date information on the types of crops, planting dates, soil conditions as well as water resources, it can be difficult for governments to make smart decisions regarding agriculture policy and planning.

Urban Planning for Smart Cities

Supporting sustainable growth taking into account the capacity of local infrastructure, any environmental barriers and without exceeding budget limits poses a major challenge to government. It is estimated that in less than 40 years, 70% of the world’s population will reside in cities and therefore policy makers need to be implementing smart solutions now in order to avoid future chaos. Such solutions can be beneficially enhanced with use of remote sensing applications. When combined with GIS software, satellite imagery plays a crucial role in applications such as land and materials classification, traffic flow management, smart utilities and energy efficiency, waste management and human population mapping. In addition, satellite data is fast and reliable and can be used to monitor the change of the city and predicting its growth.

A Digital World

Furthermore, satellite imagery is collected digitally which allows for fast delivery and unlike aerial imagery, there is no data loss during the scanning process. The data takes into account real time weather assessments to maximise the success of the collection and covers a larger ground area than possible with aerial imagery or drones. Additionally it offers logistical simplicity by cutting out the need for permits, air traffic control, equipment, pilots or personnel on the ground. This is especially important when the area of interest is in a crisis or conflict zone or the information is time sensitive.

About European Space Imaging

European Space Imaging is the leading supplier of very high resolution satellite imagery and derived services to customers in Europe, North Africa and the CIS countries. Established in 2002 and based in Munich, Germany, they have been reliably supplying imagery and supporting EU earth observation programmes controlled by the EU Commission, European Space Agency, FRONTEX, Joint Research Centre, European Maritime Safety Agency (EMSA) and others for more than 15 years

Dependable and up-to-date information is important to respond to urban growth in Sub-Saharan Africa. In Kampala, Uganda, access to very high-resolution cloud-based satellite imagery ensures dependable and timely information to help decision and policy makers to plan how to best use resources and make informed decisions.

Sub-Saharan Africa is one of the least urbanized regions in the world, yet it is expected to experience the highest rate of urban population growth in the coming decades.

In a context of widespread poverty, climate change and limited capacity to manage the rapid growth of urban population, urban growth comes with substantial costs. Cities in Sub-Saharan Africa are increasingly affected by disasters and hazards, and large urban centres are facing challenges such as overcrowding, environmental pollution and depletion of resources.

Decision and policy makers in the region need dependable and up to date information on urban growth, disaster impact and risk prediction in order to plan how to best use resources and make informed decisions. In this framework, mapping and remote sensing technologies are playing a crucial role to foster sustainable development and to address the effectively address the demanding tasks this region is facing today.

Cloud based imagery service for land management in Uganda

The rapid population growth, the increasing demand for land – both for settlement and for agriculture – and the industrial developments are driving land degradation including wetland changes in Kampala. In addition, the significant pressure on land deriving from human activities is complicated by the current complex land ownership patterns that exist in Uganda
today.

The Country is certainly facing several challenges encompassing a decentralisation of land management, scattered local and central institutions and, most importantly, a manual cadastral system of land administration difficult to keep up to date with consistent information. All these factors affect the growth of ownership’s demands of land in wetlands which many people claim through titles.

Elaborating a comprehensive and reliable land administration system for the entire country is a prerequisite to boost sustainable urban development and protect wetlands. A transparent and efficient land management system would also help to mitigate the current difficult processes associated with obtaining and transferring evidence of land ownership as well as generating a more attractive environment for investment.

Providing Very High Resolution (VHR) imagery with submeter spatial resolution of large regions through and updating them on a timely manner is crucial to create the foundational layers of a land and cadastral system with fresh and detailed information such as seamless mosaics of nations and wall-to-wall coverages

In particular, VHR imagery can be used to identify small-scale changes and heterogeneous urban structures, enabling a highly detailed analysis of the urban morphology, including the detection of single houses and infrastructure networks.

Fig. 1. Change detection imagery service on 2015 (left) and 2018 (right) over Kampala, Uganda, showing new houses and facilities near the wetlands area

Cloud-based imagery is crucial for this purpose. It can be accessed through an imagery service easy to integrate in the GIS tools of local institutions and agencies without requiring large disk storage, especially needed when performing time series analysis. Delivering the data through an imagery service enables all users to access timely, reliable and quality assured imagery directly into their applications and desktops. Hosted in Amazon Web Services using ESRI ArcGIS technology, all the imagery is optimized for the cloud and orthorectified on-the-fly using accurate DEMs. Users can utilize the multi-temporal VHR imagery service and start building valuable apps for monitoring, change detection and precision insights including land cadastres layers at scale. These valuable Earth Observation (EO) cloud-based imagery service provides the foundational product easy to plug-in into preferred GIS software packages used by land administration and cadastre agencies. In addition, the cloud-based imagery service compliments and incorporates multi thematic information sources such as legacy cadastre records.

Monitoring and preserving natural resources

The drainage of wetlands, together with inadequate provision of sanitation services to the residents of Kampala, are having further consequences and resulting in an increased pollution of water sources. This decline in water quality has implications on human health and on the economy as maintaining the quality of water has required ever increasing chemical inputs into the water treatment plants with the subsequent cost implications.

The Lake Victoria Inner Murchison Bay is one of the bays getting polluted due to human activity. The polluted surface water should be subjected to natural purification by the plants and microbes contained in the wetlands, but that is not occurring efficiently because of the large scale draining that has been ongoing over recent years. Wetlands can only be effective bio-filters under conditions of low nutrient loading and abundant swamp. Environmental monitoring and change detection are crucial to prevent a degradation of resources and public health issues. An analysis performed over imagery captured in 2015 and 2018 shows the enormous change that Murchison Bay has undergone during the last years. Wetlands loss and degradation is perfectly visible in the NIR (Near Infrared) images (Figure 1). The varying shades of red across the NIR images indicate how sensitive the satellite’s multispectral camera is to differences in vegetation cover and chlorophyll content. This is used to provide key information on plant health. Brighter reds indicate more photosynthetically active vegetation.


Fig 2. Cloud-based submetric Change Detection service using False Colours imagery (R.G,NIR) showing changes on wetlands between 2015 (left) and 2018 (right) highlighted in the yellow box. All the processing is on-the-fly.

We continued our analysis applying an NDVI (Normalized Difference Vegetation Index) analysis calculated on-the-fly over the sub-metric cloud-based imagery service, which is very useful to differentiate changes in vegetation. Figure 3 shows differences in the NDVI in the Lake Victoria Inner Murchison Bay between 2015 and 2018. Different values ranging from +1.0, to -1.0 are represented in these NDVI imagery. High levels of NDVI are represented in the green and yellow shades, while low NDVI values are pictured in the grey and pale rose colours. Very low NDVI values (for example, 0.1 or less) represent areas of barren rock, sand, or asphalt. Moderate NDVI values (approximately 0.2 to 0.5) represent sparse vegetation. Dense vegetation or crops at their peak growth stage are represented by High NDVI values (approximately 0.6 to 0.9).
This parameter is associated with the presence and healthiness of a plant. In this case, the bright green and yellow colours correspond to the algal bloom probably caused by the discharge of chemicals in the lake, which cause the overproduction of algae triggering a process called eutrophication.


Fig. 3 Cloud-based Change detection imagery service calculating NDVI index on-the-fly show the presence of vegetation, in Inner Murchison Bay, Lake Victoria between 2015 (left) and 2018 (right). The green and yellow colours, representing high NDVI values, in the right imagery show the presence of high concentration of vegetation into the water.

The benefits of analytics-ready imagery services on the cloud

As showed in the previous section, cloud-based imagery services are crucial to fulfil the information needs to boost sustainable development and planning, providing up-to-date and sub-metric information data that can be used for the following purposes:

- As a base-map layer;
- To identify land that is suitable for development;
- To map and create digital models of features such as buildings, river streams, landmarks;
- To monitor the progress of projects;
- In combination with business intelligence software to compare project delivery figures against project areas;
- To identify and map informal settlements and visual counts of informal structures.

Very often, the images that governments and private companies have access to are outdated by two, three, or even more years. Thus, it is of utmost importance to provide them with timely updated imagery.

Additionally, some entities may rely on free sources of imagery that could be used for base-mapping, but the resolution of this data generally does not meet the parameter of sub-metric resolution that is needed for a thorough analysis and identification of independent structures and buildings. Another challenge when monitoring the progress of a project over a period of time is the amount of data and the large storage needed to store the imagery.

Delivering the data through a friendly-user imagery service provides a solution to all these challenges. In order to trigger the imagery service, users just need to define their area of interest, the frequency with which they need the data and their application or resolution needs. This enables users to easily access fresh, reliable and quality-assured imagery, directly onto their apps and desktops.

Hosting the data in Amazon Web Services using Esri ArcGIS technology, allows the user to have access from various devices and locations. The data doesn’t need to be downloaded nor stored. All the imagery can be accessed on the cloud and users can utilise the multi-temporal imagery service to start building valuable applications for monitoring, change detection and precision insights on the fly. In addition, the imagery service can be easily integrated through plugins in the users preferred GIS software packages.

Whether users are future-focused or exploring the past, they can get constant and reliable access to seamless data on the cloud and get any area of interest, every day, directly into their applications and desktops.

All picture Credits: Deimos Imaging, an UrtheCast Company

EARSC is a partner of the Geospatial World Forum 2019!

Overview

Geospatial World Forum is a collaborative and interactive platform, which demonstrates collective and shared vision of the global geospatial community. It is an annual gathering of geospatial professionals and leaders representing the entire geospatial ecosystem.

This comprises of public policies, national mapping agencies, private sector enterprises, multilateral and development organizations, scientific and academic institutions, and above all end users from government, businesses, and citizen services. With Geospatial Media and Communications as the primary driver, Geospatial World Forum is conceived, designed and managed by a partner network of about 50 organizations globally.

In January 2018, the platform celebrated its 10th anniversary in Hyderabad, India. Over the years, Geospatial World Forum has become the most talked about geospatial event, best-known for its futuristic themes, engaging content, and top-level attendees. Back to Europe after 2 years, Geospatial World Forum 2019 is committed to creating a premium platform for geospatial community to learn, share, connect, brand, and network with stakeholders associated with the industry.

Theme
#geospatialbydefault – Empowering billions!
The Fourth Industrial Revolution, driven by AI, Big Data, IoT, and Robotics, is bringing significant attention to geospatial technology and expanding its reach to larger masses of the society. Geospatial technology is now empowering IT-enabled services and optimizing engineering workflows and business processes.

Being an integral part of this disruptive journey, geospatial industry is now open to larger market drivers, creating new growth opportunities. The hidden treasure of spatial thinking is being unveiled through collaborative, interactive, and more user-friendly platform. Simplifying utility and value of geospatial knowledge for consumers became a determining factor for successful business models.

While disruption gets to be the new normal, geospatial is becoming ubiquitous, pervasive, and ‘default’ in our daily lives. Join the #geospatialbydefault movement at Geospatial World Forum 2019 as we strive to make geographic information a common language for 7 billion people around the world.

Register now! here

HyperScout 1, the first miniaturized hyperspectral imager for space, successfully demonstrated that it is possible to process acquired satellite data on board. By knowing the position of the satellite and in which direction it points, the instrument knows what it is looking at and can interpret the data, thus eliminating the need to download the data . The HyperScout 1 camera, launched in February on board the GOMX-4B satellite, produced the so-called Analysis Ready Data (ARD) hereby successfully demonstrating the onboard data processing workflow for the first time.

When flying a satellite that takes images of the Earth, it seems logical to download the data and process it on Earth. However, there is a strong trend towards smaller satellites and instruments but without reducing the imaging capabilities. The disadvantage of using these CubeSat systems is its limitation in data processing and downlink capacity. Fortunately, it is also not necessary anymore. The HyperScout 1 instrument, one of which was launched on the GOMX-4B satellite in February, now successfully demonstrated that it is possible to process data on board reducing the downlink capacity.

“WITH THIS ACHIEVEMENT WE MAKE A NEW WAY OF OPERATING SATELLITES POSSIBLE, WITH THE POTENTIAL TO CHANGE THE WAY WE PROCESS ALL DATA IN SPACE.”

Alessandro Zuccaro Marchi, optical engineer and technical officer – European Space Agency

“We specifically developed the hardware and software for HyperScout to make this possible”, explains Marco Esposito, manager of the remote sensing unit of cosine, the company that developed HyperScout.
Bavo Delauré, project manager of Belgian research institute VITO, adds: “The algorithms are derived from our developments for the PROBA-V mission. PROBA-V data is however processed on the ground in a large data center so the algorithms were tailored for implementation onboard the cubesat-instrument”. S&T Norway turned the algorithm into on-board software which was uploaded to the satellite after launch. The HyperScout instrument took about one minute to process the images into Analysis Ready Data in orbit. Downloading the raw data would have taken several weeks from a nanosatellite. Even for larger and more expensive platforms, the data downlink can take several hours. Marco Esposito of cosine points out: “The on-board processing workflow used by HyperScout enables a paradigm shift in the use of a space asset, by serving application specific customers with real-time information without the need to downlink raw data”.

HyperScout processes the data on board by correcting for the curvature of the Earth and the angle under which it is observed, so-called orthorectification, and determines which position on the ground corresponds to the pixels in the camera, called georeferencing. It also corrects for the sensitivity of the instrument in the different wavelengths it observes. With this information available, it is possible to analyze the images on board. This new data processing workflow offers our customers to upload new algorithms on board any time and make analysis when needed, for example to detect fires, flooding or irrigation needs.

The first HyperScout 1 instrument was launched into space on 2 February 2018, on board the nanosatellite GOMX-4B of the European Space Agency (ESA). HyperScout was developed by an international consortium led by cosine with partners S&T, TU Delft, VDL and VITO. The development and launch of the first HyperScout was funded through the ESA GSTP program with contributions from the Dutch, Belgian and Norwegian national space organizations (Netherlands Space Office, BELSPO and Norsk Romsenter).

More information about HyperScout can be found on hyperscout.nl

Satellites view the Earth as a whole – collecting data without regard to political boundaries. In an ever-changing and uncertain world, very high resolution (VHR) satellite imagery is fast becoming a common tool to predict future threats, monitor development outcomes and minimise risk at all levels of government. As such, policy makers now need to be provided with more information than ever before and usually this information is time critical.

Information derived from optical satellite imagery provides a whole new way of looking at the world. As well as tabled data, VHR imagery can provide a 3D overview of the state of the Earth and allows you to see the current situation in near-real-time, permitting optimised responses for the best possible outcome. It adds another level of detail that can serve numerous purposes and is an indispensable source of information gap filling.

Security Surveillance for Safer Borders
The power of VHR data lies in the detail. It can provide empirical answers to questions concerning multiple humanitarian and border security applications. Due to the resolution of the imagery, tents and cars can easily be identified from the sky allowing the movement of refugees to be monitored in addition to the mapping of displaced populations. The technology also provides more measured border security controls both at a domestic and international level. Oceans are large and ships are small however through the aid of satellite technology, policy makers knowledge of the entire ocean and not just coastal zones, can be significantly increased. The wide reach of the technology also means that no area of the ocean is unable to be captured. As a result, countries can reduce the number of illegal immigrants entering, reduce the death toll of human lives at seas and increase internal security within the country by preventing cross-border crime.

Agriculture Insights for Modern Frameworks
VHR imagery provides the opportunity for multispectral analysis to be conducted. With multispectral imagery, it is possible to extract additional information that the human eye fails to see. Too often the issue regarding the lack of basic information required for sustainable food security poses a threat to governments. Without up to date information on the types of crops, planting dates, soil conditions as well as water resources, it can be difficult for governments to make smart decisions regarding agriculture policy and planning.

Urban Planning for Smart Cities
Supporting sustainable growth taking into account the capacity of local infrastructure, any environmental barriers and without exceeding budget limits poses a major challenge to government. It is estimated that in less than 40 years, 70% of the world’s population will reside in cities and therefore policy makers need to be implementing smart solutions now in order to avoid future chaos. Such solutions can be beneficially enhanced with use of remote sensing applications. When combined with GIS software, satellite imagery plays a crucial role in applications such as land and materials classification, traffic flow management, smart utilities and energy efficiency, waste management and human population mapping. In addition, satellite data is fast and reliable and can be used to monitor the change of the city and predicting its growth.

A Digital World
Furthermore, satellite imagery is collected digitally which allows for fast delivery and unlike aerial imagery, there is no data loss during the scanning process. The data takes into account real time weather assessments to maximise the success of the collection and covers a larger ground area than possible with aerial imagery or drones. Additionally it offers logistical simplicity by cutting out the need for permits, air traffic control, equipment, pilots or personnel on the ground. This is especially important when the area of interest is in a crisis or conflict zone or the information is time sensitive.

About European Space Imaging
European Space Imaging is the leading supplier of very high resolution satellite imagery and derived services to customers in Europe, North Africa and the CIS countries. Established in 2002 and based in Munich, Germany, they have been reliably supplying imagery and supporting EU earth observation programmes controlled by the EU Commission, European Space Agency, FRONTEX, Joint Research Centre, European Maritime Safety Agency (EMSA) and others for more than 15 years

Datacubes are trending, and with the rasdaman datacube engine they can even be federated across data centers. Users benefit from location transparency and planetary-scale fusion services. Now public and private datacubes get federated – which, however, raises new technical challenges in terms of security and billing.

The BigDataCube project, supported by the German Federal Ministry for Economic Affairs and Energy, aims at advancing the innovative datacube paradigm – i.e., analysis-ready spatio-temporal raster data – from scientific into commercial data centers. To this end rasdaman, “the worldwide leading” (ESA, 2017) datacube technology, is getting installed on the public Sentinel hub CODE-DE as well as in the commercial cloud environment of cloudeo AG. A specific new challenge on which BigDataCube focuses is versatile role-based access control on datacubes, configurable down to the level of single pixels.

Under the lead of Jacobs University the team of rasdaman GmbH (datacube backend), cloudeo AG (commercial geo cloud), and DLR (weather and ocean analytics tool) collaborate on these services. On CODE-DE, the datacube service is going to complement the batch-oriented, Hadoop-based service of CODE-DE with interactive spatio-temporal viewing, fusion, and analytics services on Sentinel satellite imagery, based on the open OGC standards.

At this stage, the cloudeo datacube and the DLR analytics tool on top of rasdaman are operational, and so is the precursor version of the CODE-DE datacube service. This precursor has been established while CODE-DE is preparing the infrastructure for the datacube engine. Based on sample Sentinel 1 and 2 timeseries it offers a broad set of access, formatting, filtering, processing, and general analytics functionality through a variety of common Web clients.

Read more: BigDataCube.org

Contact: Dr. Peter Baumann, baumann@rasdaman.com.

Antwerp, September 2018. At this year´s INSPIRE Conference a hot topic was coverages, more specifically: raster data. Experts showed how to use coverages, and solution paths for the remaining issues so that coverages can be served simultaneously by both WCS and SOS.

INSPIRE addresses many types of raster data in Annex II and III – Orthoimagery, Elevation, Geology, Atmospheric conditions and Meteorological geographical features, Oceanographic geographical features, Soil, Land cover, Natural risk zones, Energy resources, and more. The common concept for modelling raster data is adopted from OGC coverages as specified in the Coverage Implementation Schema (CIS) standard, which meantime is also adopted verbatim by ISO as 19123-2. INSPIRE, though, has adopted coverages with certain deviations which turn out to be troublemakers as implementation progresses. Therefore, a group of three renowned experts has teamed up to resolve issues and achieve harmonization with OGC CIS: Jordi Escriu (Carthography and Geographical Institute Catalonia, Spain, INSPIRE expert), Peter Baumann (Jacobs University, coverage expert), and Katharina Schleidt (DataCov Austria, SOS expert). At the INSPIRE conference the group presented their results in the workshop “Practising INSPIRE Coverages – Enhancing your Datacube Implementation Assets”.

“Spatio-temporal coverages, including datacubes, comprise a powerful tool to provide INSPIRE and Coperncius data in an integrated, easy to access manner” summarizes Peter Baumann, CIS editor, and adds, “with only few adjustments we can achieve analysis-ready data and, as extra benefit, a substantial harmonization between the SWE and coverage worlds”.

As it turned out only rasdaman has the flexibility for the coverage experiments conducted in the investigations, and so rasdaman naturally was chosen as the vehicle for modeling, showcasing, and discussion at the workshop. Participants could recap the examples shown no their laptops. After the workshop, attendants used the opportunity of rasdaman’s fair booth to see “datacubes on steroids” in multiple scenarios and with dynamic querying.

Currently, the findings of the INSPIRE coverage expert group are being published and presented to JRC so that the necessary minor adjustments can be discussed and adopted in due course to allow stakeholders to proceed swiftly.

Impact
The technological development in the fields of aerial/space technology, computer vision, and image processing, provides new tools and automated solutions for 2D/3D mapping and reconstruction. However, the accurate and reliable 3D reconstruction as well as the fully exploitation of remote sensing data for feature extraction and object detection of complex scenes, such the industrial ones, still remains challenging. Research activities that combine satellite remote sensing data and Aerial Laser Scanning (ALS) point clouds (well known as LIDAR) have increased in recent years to exploit both: the available rich spectral image information from satellite sensors and the good geometric quality of LIDAR point clouds. Sentinel-2 data from ESA’s Copernicus program can play a key role to this methodology (https://sentinel.esa.int/web/sentinel/home).

Concept
This study explores the complementary use of Sentinel-2 data with LIDAR point clouds at industrial scenes for: 1) 2D/3D mapping, 2) feature extraction and 3) object detection. A complex industrial area of 4.3 km2 near at Patras city, Greece, was used as case study. Several 2D/3D feature-spatial data products were extracted using the Erdas Imagine software (Raster and Point cloud tools, Terrain analysis tool, VirtualGIS tool, Machine Learning tool and Spatial Modeler).

Technical Details

Data description
At first step, the LIDAR point clouds and the Sentinel-2 images were collected over the area of interest for the same time period. Concerning the Sentinel-2 images (type MSIL2A), the Copernicus Open Access Hub (https://scihub.copernicus.eu/) was used. Concerning the LIDAR point clouds, the adjustment of neighboring LIDAR strips was firstly performed through strip alignment and then a georeference process using ground control points (GCPs) and check points (CPs) was carried out afterwards. LIDAR point density varied considerably over the whole block depending on the LIDAR strip overlap, i.e., 5 points/m2 and 30 points/m2 for regions covered by only one strip and more than one strip respectively. Multiple echoes and intensities were recorded. Concerning the used GCPs and CPs: 1) were consisted of characteristic points (e.g., corners at buildings, etc), 2) were measured by the ComNav Τ300 receiver station both on GPS/RTK and GPS/Relative static modes, and 3) their coordinates were calculated using the GNSS network of reference stations of SmartNet Europe/MetricaNET.

2D/3D mapping
The LIDAR point clouds were classified and refined to extract the bare-earth points. The bare-earth points were used to extract the corresponding Digital Terrain Model (DTM) (Figure 1) while the total LIDAR point clouds were used to extract the Digital Surface Model (DSM). The orthoimage of the area of interest was generated using the LIDAR/DTM (Figure 2). The corresponding coloured LIDAR point clouds were also extracted (Figure 3).

Figure 1: Extraction of bare-earth points and generation of the orthoimage.


Figure 2: Superimposition of the DSM to the orthoimage.

Figure 3: LIDAR point clouds coloured (RGB) from Sentinel-2 data.

Feature extraction
Proper features were calculated through Spatial Models (Figure 4) to distinguish built-up areas from bare soil, vegetation, roads, etc, such:
- Intensity (from LIDAR data),
- Normalized DSM-nDSM (from LIDAR data),
- Combination 4/3/2 (from Sentinel-2, pixel size of 10 m)
- Combination 8/4/3 (from Sentinel-2, pixel size of 10 m)
- Band Ratio for Built-up Area-BRBA (from Sentinel-2, pixel size of 10 m)
- Combination 12/11/4 (from Sentinel-2, pixel size of 20 m)
- Combination 11/8A/2 (from Sentinel-2, pixel size of 20 m)
- Bare Soil Index-BSI (from Sentinel-2, pixel size of 20 m)
- Normalized Difference Water Index-NDWI (from Sentinel-2, pixel size of 20 m)

Figure 4: Extracted features through Spatial Models.

Object detection
The industrial areas include buildings premises and structures with several complex shapes (e.g., tanks, etc). Typical LIDAR point cloud classification techniques cannot distinguish buildings from such structures. To this end, several machine learning techniques (SVM, CART, KNN, Naïve Bayes and Random Forest) fed by several combinations of features (Multi Dimensional Feature Vectors-MDFVs) were performed and evaluated for a sub-region (Figure 5). Training samples for three classes were collected: 1) Buildings 2) Ground and 3) Structures. The best results were achieved via the combination of CART+MDFV3 (Figure 6). To optimize the results, a post process was performed through a majority voting filter and regularization methods. Figure 6 also shows the 3D models of the buildings and structures of the area of interest in Level of Detail 1 (LoD 1).

Figure 5: Considered MDFVs: Each MDFV includes several features (left); Example of a Spatial Model for the training and classification process of the machine learning method “Random Forest” (right).

Figure 6: The best results were achieved via the combination of CART+MDFV3. The 3D models of the buildings and structures of the area of interest in LoD 1 were automatically extracted.

Conclusions
This study explores the complementary use of Sentinel-2 data with LIDAR point clouds (augmented with additional information such intensity) for 2D/3D mapping of complex scenes such the industrial ones. The results illustrate the functionality and the utility of such multi-modal approach. Proper features from both datasets can contribute to distinguish built-up areas from bare soil, vegetation, roads, etc, especially by feeding machine learning techniques with high generalization capabilities.

Contact Info
o Contact person : Maltezos Evangelos, Vasiliki (Betty) Charalampopoulou
o E-mail: mail@geosystems-hellas.gr

A part of the Horizon2020 programme funds space-related projects through the so-called “Space Call”. To a large extent, this part of the programme concentrates on Copernicus-enabled applications and services.

Nevertheless, there are other elements of the Horizon2020 instrument that might be relevant for Copernicus-related initiatives.

To encourage scientific endeavours, the European Commission Directorate General for Internal Market, Industry, Entrepreneurship and SMEs (DG GROW) has put together a list of Horizon2020 calls that can be of interest to anyone working on Copernicus or Earth Observation in general.

Most of these calls have already been published and opened for proposals. They represent a significant opportunity for the Copernicus community. The deadline for the Space calls ends in March 2019.

Source

An editorial by Philippe Brunet, Director for Space Policy, Copernicus and Defence at the European Commission.

A short while ago, actors the Copernicus ecosystem gathered in Brussels for its traditional annual eponymous event: the Copernicus Ecosystem Workshop.

For one and a half day, 250 representatives from the European Commission, delegates from Participating Countries, from industry, from academic and research institutions, and Copernicus entrepreneurs were able to exchange and network in an informal setting. The idea was not to celebrate the programme’s many successes, but to look into the future, into the role of the ecosystem in general and of the industry in particular in Copernicus’ future development, and into the further growth of its user base.

For me and my team, it was obviously a pleasure to see so many familiar faces, and to meet newcomers who have become part of the ecosystem since last year. But it was first and foremost an occasion to listen. To listen to what the representatives of the various “species” that make up the ecosystem have to say about the future and about the many Copernicus market development initiatives that have borne fruit in 2018 (e.g. the DIAS Data and Information Access Services platforms) or have been recently launched by the European Commission (e.g. Copernicus Skills Programme or new elements of our start-programme such as the Copernicus Hackathons).

With seven satellites in orbit, the core of our constellation of Sentinel is now complete. With the launch of the Copernicus Climate Change Service’s Climate Data Store, we can now proudly proclaim that we have developed six operational services at the service of users in Europe and beyond. Our data distribution system is improving at a rapid pace, while our user base is growing at record speed and shows no sign of having reached a plateau.

This success is not only a success of the European Commission. The members of the Copernicus ecosystem deserve our praises and thanks, as they have vastly contributed to this magnificent showcase of what the European Union can achieve when common, public and global good is the objective of a collaborative effort. No single EU Member State, no country in the world could have developed an Earth Observation system of systems as ambitious and successful as Copernicus. We, of course, needed the combined financial resources, but more than anything else, we needed the vision as much as the complementary scientific and industrial capabilities of the Participating Countries.

Indeed, Copernicus is highly sought-after internationally and the international presence of the programme is growing through a set of Cooperation Arrangements which in many cases allow us to access additional Contributing Missions, provide a new source of in situ and validation data, but also provide new business development opportunities to European service providers.

But we should in no way believe that the job is done. Technology is evolving, the industry is changing with the rise of the New Space actors, user requirements are evolving, and new ones emerge, while new users are looking into our data and information.

We therefore need to continue to grow the programme. This is why the European Commission is seeking a budget of € 16 billion for the next 2020-2017 Financial Framework, of which € 5.8 billion are earmarked for Copernicus. We are also looking into expanding our fleet of Sentinel to fill observation gaps in areas such as CO2 monitoring from satellites or thermal remote sensing. But, above all, we must ensure the continuity, the stability and the predictability of the future of the main components of the programme. Indeed, these three elements are a condition sine qua non of the investments by industry and users, of the market development and data uptake.

Copernicus is a public programme and should therefore keep the general societal good at its heart, address negative externalities and address the challenges of the next 15 years, in particular climate change and security. It should invest in areas in which the private sector is not willing or able to venture. Its first objective is to play an ever-increasing role in support of policy-making and implementation at European, national, local but also at international level, for instance to monitor compliance of international agreements aiming to fight climate change.

A second objective should remain to support innovation, and by consequence the creation of jobs and economic growth. In this regard, the full, free and open access to Copernicus data and information should continue to be the cornerstone of the programme. The best way to maximise the societal and economic potential of Copernicus is to put the data in the hands of as many users, organisations or individuals as possible, so that innovative ideas and solutions can emerge. Our data policy is an enabler, a trigger of economic development, and a direct contribution to European and global welfare and sustainable development.

We will continue to support both the supply and the demand sides of the Copernicus ecosystem. But we, at the European Commission, cannot do it alone!

We, of course, need the support of the European Parliament and of the Member States. But we also need industry to play its role. To write the scenario of Copernicus Season 2, industry must definitely be part of the casting.

I was happy to hear at the Ecosystem Workshop that industry is ready to take the lead, with adequate support from the EC, and that buying services rather than infrastructure is the way forward. We, at the EC, are prepared to provide the required anchor tenancy support, with adequate public funding, to continue facilitating access to the data, support research and innovation as well as access to finance, while stimulating demand through Copernicus services procurement contracts.

Copernicus does not belong to the European Commission. It is funded by taxpayers’ money and therefore belongs to the citizens of the EU, and, ultimately, to the citizens and ecosystems of our fragile planet. They should take the future of the programme into their hands!

The past year has been important in the life of Copernicus. Many crucial milestones have been reached, on time and on budget, but there is much more to come. I look forward to measuring the progress made and to meeting many new happy users at the 2019 Copernicus Ecosystem Workshop.

Source