GeoMonday 2017.3 – Natural language understanding in web mapping applications

conterra-logo “Will speech soon do away with typing” – This question has recently been raised by a large German Newspaper. Lately, more and more speech assistants like Google Assistant, Amazone’s Alexa, Microsoft Cortana or Apple’s Siri are reaching the market and all owing users to control many parts of their life by voice input. This Technology is called natural language and understanding (NLU) and may also be used to control web mapping technology. Imagine that you could say “show me all schools in Berlin” instead of using a selection tool to select those features.

Matthias Stein is a software engineer at con terra GmbH. Previously he studies Bild_Mathias_SteinGeoinformatics at the Bochum University of Applied Science.

Martin Wilden studies Geoinformatics at the University of Münster and  worked as student assistant for 52° North Initiative for Geospatial Open Source Software GmbH. Bild_Martin_WildenAfter studying he joined con terra GmbH as software developer.

 

Advertisements

GeoMonday 2017.3 – From aerial images to maps with Deep Learning

TerraLoupe_logoWith the increasing amount of aerial imagery – regardless if captured from aircrafts or UAV  – available, automatic analysis of this data becomes more and more important to make use of this data. TerraLoupe uses deep neural networks to automatically detect objects of interest for various industries such as automotive, insurance or energy to help their clients getting deeper insights for their business critical applications. This includes high-definition maps for autonomous driving, risk assessment for insurances and solar potential analysis.

sebastian_gerke

Sebastian Gerke studied Computer Science at the University of Karlsruhe, after which he worked as a research associate at the Fraunhofer HHI and pursued research in computer vision and machine learning. In 2015 he co-founded TerraLoupe, a startup that brings deep learning expertise to the field of aerial imagery.

GeoMonday 2017.3 – How neural networks make GIS-supported crop production more efficient

EsriDeutschlandHigh-tech has already arrived in agriculture. Modern agricultural machinery and geographic information systems make precision farming possible. An important aspect in crop production is the basic fertilization with nutrients and additives. The pH value can already be determined in a small scale and during the crossing of a tractor with specific sensors. For essential macronutrients like phosphorus, on-site soil sampling as well as complex and cost-intensive determination of the content in the laboratory are still necessary. Phosphorus content depends on chemical and physical soil conditions. If these conditions are known, the content of phosphorus can be estimated. This paper provides extracts from a research project on how neural networks help to estimate local phosphorous content for fertilization by learning those nonlinear multilateral relationships in the soil.

mmarz

Michael Marz is a sales engineer at Esri Deutschland GmbH. Previously, he was a scientific staff member at the University of Halle and conducted research in the thematic field of efficient crop production with focus on fertilization and self-learning algorithms.

GeoMonday 2017.3 – Artificial Intelligence

Nowadays „Artificial Intelligence“ celebrates its comeback to the top-IT-buzzword-lists. Neverthless, the topic is around for decades. But in the recent years, significant progresses has been made. We see a wide range of new business models and applications also in the geo area, which are made possible by ever-improving pattern recognition algorithms and machine learning technologies. Transforming geodata into loaction meaning also powers next generatio decision-making systems that are now being available for all kind of users. More and more systems are becoming at least semi-autonomous and proposing smart suggestions, which will change the way we interact with and perceive geo-spatial applications.

Date: 18th of September 2017

Time: 7:00 pm

Place: Office Club Berlin, Pappelallee 77/78, 10437 Berlin

Get your tickets for the 3th GeoMonday 2017 now at https://geomonday2017-3.eventbrite.de

 

GeoMonday 2017.1 – The Full Exploitation of Open GI

ENERGIC_logoThe European project ENERGIC-OD (European Network for Redistributing Geospatial Information to user Communities – Open Data) address the heterogeneity of GI world and the lack of the single system which could satisfy the different user-requirements in world of geoinformation. The adopted approach is by utilising a brokering architecture and deploying a set of virtual hubs and a single point of access to geospatial datasets. This approach facilitates the development of multidisciplinary applications, based on full exploitation of open GI.

Studied Architecture and urban development, Frank Iden started as an Urban planner and Architect. Later he founded his own firm in 1992, SRP GmbH, where the Geographical Information Systems were developed for “Senate department for urban development and environment Berlin”. The interdisciplinary information system (Fachübergreifendes Informationssystem, FIS), the Geoportal of Berlin (FIS-Broker), and specialised procedures for city, landscape, environmental planning are among their products.

GeoMonday 2016.3– Impressions

A big thank you to all the speakers and also to the audience. It was a great evening, full of interesting Geo-Topics and yummy pizza.

For everyone who could not be there or would like to recall some information, we will publish the slideshows and the video very soon.

We are looking forward to seeing you on the next GeoMonday on the beauty of maps. Keep checking this blog for updates.

GeoMonday 2016.3 – The Potential of VR

Photogrrealities-ioammetry has been around for over 150 years and its first and foremost usage was measurements and cartography. With the reinvention of structure from motion algorithms and the immense increase in computation power new potential got unlocked. With the automated extraction of 3D data meshes can be created automatically and the images can be mapped on the 3D surface. Digital Maps already transition to full 3D reconstructions. The recent developments not only have an impact on the Geospatial Industry, but also in other fields. Image mapped 3D reconstructions have a high visual fidelity and because of this get used more and more visual effects and very recently videogames. With VR the potential further increases as VR makes you feel like you are there. Feeling fully present in a 3D scene makes reconstructions of the real world incredibly interesting as you essentially “teleport” to a different place. The huge importance of this is emphasized by the fact that Facebooks interest in VR is essentially to create a teleporter.

David Finsterwalder is the Founder and CEO of realities.io. Working in Archeology david-finsterwalderhe gained profound knowledge in 3D Reconstruction through LiDAR Scanning, UAV and Ground Photogrammetry. Driven by the question how to unlock the potential of the gathered data for public relations and museum context he started to look into realtime 3D graphics and eventually VR HMDs for visualization. Amazed by all the possibilities for scene reconstructions and VR HMDs for Archeology and beyond he founded realities.io.

 

GeoMonday 2016.3 – VR is dead, long live AR!

csm_bild-wort-marke_auf_weiss_1280x853_fb0b60252f

The hype about VR is in full swing. There is hardly any other technology, that dominates the Entertainment market to that extent. There are basically two species of VR goggles. Most of them are wired or connected to smartphones, which are commonly used in the entertainment industry. AR technology is mainly used to enrich print media or in marketing. Usually this is achieved through the usage of smartphones. Several manufactures offer AR glasses, which could not get a hold in the market. AR lead a niche existence compared to VR. In spite of these leading signs, Robert Meyer states, that the future is AR and VR is obsolete by now already. This presentation shows similarities and differences of the two technologies. We hope to discuss the potential of devices like the Microsoft HoloLens.

Robert Meyer is researcher at HTW Berlin –  Department of Informatics, Communicationrobert-meyer and Economics. Human-Computer-Interaction in virtual realities has been a core interest of Robert Meyer for years. The current thematic complex is based on the transition of game technology in business and industry applications. Robert Meyer is not only a developer but also has contributed to numerous scientific conceptions within this field.

GeoMonday 2016.3 – The Digital Snapshot of Reality

hpi

Remote sensing technology such as LiDAR and image matching algorithms are used for a periodical acquisition of our physical world. Countries, cities, sites, and assets are captured every year, every day, every hour, and every minute. The resulting 3D point clouds are a digital snapshot of the reality and allow to derive information and insights. In this talk, we present techniques to manage, process, and analyze large-scale 3D point clouds. These techniques are relevant for a variety of applications to get new insights, detect changes, and establish workflows for updating and maintaining of existing geo data (e.g., 3D city models, terrain models, tree cadastre).

Rico Richter is a research scientist with the computer graphics systems richter_photogroup of the Hasso Plattner Institute at the University of Potsdam, Germany. He has many years of experience in the development of complex processing, analysis, and visualization techniques for massive point clouds. His main focus are research and industrial IT solutions for the management and application of large-scale, highly detailed point clouds.