The adequate acquisition and analysis of a scene are of great interest for photogrammetry, remote sensing, computer vision, computer graphics and robotics. In this regard, 3D data have become a standard data source for numerous applications. The capability to interpret such 3D data, in turn, allows dealing with a variety of high-level tasks such as scene modelling, autonomous exploration of unknown scenes or autonomous navigation without collisions. To obtain such a capability, many applications rely on a semantic interpretation of the acquired data. In this course, we will first provide an overview of different concepts to obtain 3D data either directly by measurements or indirectly from acquired imagery. Subsequently, we focus on the semantic interpretation of 3D data. Thereby, we will present the classic approach relying on the use of handcrafted features and the state-of-the-art end-to-end learning approach relying on deep learning techniques.
The course introduces recent classification schemes with the goal to produce and update 2D topographic databases. The inclusion of the spatial descriptors such as geometry and shape are important to characterize topographic objects in orthoimages. This course will present some of the challenges in mapping from high- resolution orthoimages and highlights the necessity of characterizing the orthoimages in the spatial domain. The solution to the above challenges will be provided by the efficient tool called morphological attribute profiles. They are multi-scale attributes and are constructed by a hierarchical representation of the images, thus enabling object-based image analysis. These characterizations are classified using well-established machine learning methods and different data sources (either raw or derived features). Different approaches to assess the thematic and geometric accuracy of map data will be discussed, and lastly the cartographic enhancement of the classification maps at different levels of quality will be presented. Solutions to the tasks are given by means of detailed course material including open source programs.
Deep Learning has led to significant breakthroughs in various fields including natural language processing and computer vision. Remote sensing also benefits from such methodological advances and deep networks currently achieve state-of-the-art results in many automatic tasks, such as object detection, semantic segmentation (e.g. for land cover mapping), change detection, etc. The goal of this course is to introduce deep learning, review the main architectures relevant for cartography, photogrammetry and other EuroSDR related fields, as well as to train the participants with available software and codes. The audience will be offered to know about and practice with recent architectures proposed by the lecturers.
It is complementary to the course “Topographic Maps through Description and Classification of Remotely Sensed Imagery and Cartographic Enhancement” that focuses on the traditional approach to automated classification (i.e. feature extraction and supervised classification) while deep learning brings a paradigm change by learning both the features and the classifier, at the possible cost of higher labeled datasets and higher computational resources.
There is an increasing awareness amongst practitioners in both the geospatial and Architecture Engineering and Construction (AEC) communities that enabling interoperability and moving towards integration of data from the two domains can provide benefits to sectors such as construction, asset management, safety and security, local and regional planning and building permit processes, national mapping agencies and many more.
Taking a data-driven perspective on interoperability and integration – i.e. looking at the integration of Building Information Modelling (BIM) and geospatial data - the course will provide a comprehensive overview of GeoBIM, starting from first principles - comparing BIM and Geo, identifying opportunities for using integrated data and challenges arising. Two case studies then give the opportunity to explore the topic more in depth – planning/permits processes and asset/facilities management. The course concludes by allowing students to explore GeoBIM in a wider context, as a location-enabled foundation for digital twins, smart cities and the internet of things.
Various examples from practical applications and hands-on practical work will illustrate the theory.
This introductory course aims to provide a comprehensive overview on the state-of- the art in Open SDI and its key components, and introduce participants to the underlying principles of Open SDI, and let them experience hands-on what it means to establish and maintain an Open SDI. A number of topics will be tackled: spatial data infrastructures as well open data principles, key standards, architectures, (network) services, relevant EU-regulations and policies, governance strategies, and key institutions. At the end of the course, participants are: informed about Open SDI strategies around the world, aware of the main strengths, weaknesses, opportunities and threats of Open SDI, familiar with the latest technological developments, capable to facilitate the opening of open data using latest developed tools, and able to evaluate Open SDIs.
The recent decade has brought tremendous progress in Airborne Laser Scanning (ALS), the state-of-the technique for 3D mapping of topography and shallow water bathymetry. The pulse repetition rates increased from the kHz to MHz level and, together with the introduction of single photon sensitive receiver arrays, this boosted both the achievable point density and area coverage performance. LiDAR point cloud classification further profited from multi-spectral laser scanning using infrared and green wavelengths and from concurrent capturing of image and scan provided by modern hybrid sensor systems. Green lasers are used for measuring underwater topography, also referred to as bathymetry, laser bathymetry. Airborne Laser Bathymetry is no longer restricted to charting shallow coastal areas only but evolved to a powerful tool for high resolution mapping of the entire littoral area, referred to as topo-bathymetric LiDAR. Finally, sensor miniaturization and progress in aviation technology has opened new close-range airborne applications due to integration of lightweight LiDAR sensors on Unmanned Aerial Vehicles. All these topics are covered in the EuroSDR distance course “Recent LiDAR technologies”.
In this course, the participants will refresh the basics of ALS, will learn details about the above mentioned technologies in theory, and will also process provided sample data in hands-on sessions. For the theory part of the course, respective papers, text book excerpts, and slides will be provided along with short pre-recorded videos. The scientific laser scanning software OPALS is the basis for practical data processing. The participants obtain a temporal personal scientific license in advance, so that they can already familiarize themselves with the software before the actual start of the course. The examination consists of multiple choice tests (theory) and short technical reports (exercises).The course is divided into the following six modules.
This is an introductory course to Spatial Linked Open Data. Linked Open Data is a standards-based approach for data interoperability. In this course, we will teach the basic theory of Linked Data, and introduce the most important standards such as RDF. More in-depth the topic of data modelling, vocabularies and ontologies will be elaborated as one of the key concepts of Linked Data (module 2). Although the concepts and technology is generic and not specific for spatial data we will discuss in particular the context of spatial data on the web (module 1). The second part of this course is split in a technical module (module 4) and a business module (module 3). The business module will discuss the business case for linked data implementations based on the case study of the Dutch Kadaster, one of the earlier linked data implementations in Europe. The technical module will provide best practices on how to convert data into linked data, and will be practical hands-on creating SPARQL queries.
Up to recently geographic data was exclusively available from authoritative sources such as National Mapping and Cadastral Agencies, professional companies, etc. The rapid emergence of Volunteered Geographic Information (VGI) and Crowdsourced Geographic Information (CGI) (referred to for brevity as V&CGI in this document) has challenged and changed this situation. V&CGI have transformed from being considered ‘disruptive’ and poor quality to well-known mainstream data sources used widely in industry, research, and other applications. The goal of this course is to introduce participants to V&CGI, the current state-of-the-art research in these areas, methods for obtaining V&CGI data (API sources, processing GeoJSON, etc), and advanced topics such as assessment of the quality of these data. Various examples from practical applications and hands-on practical work will help illustrate the key characteristics of V&CGI data. These practical examples will also help participants to explore the opportunities provided in terms of research, geospatial data integration, etc. by data sources from V&CGI. The course will also equip participants with a suitable blend of the current theory and practice around understanding the quality of V&CGI data and assessing its fitness for different purposes and applications. Free and open source software and openly accessible V&CGI will be used without any need for special hardware or software installations.