Mapillary Hires Award Winning Computer Vision Team to Lead New Research Lab in Graz, Austria

MALMO, SWEDEN--(Marketwired - May 19, 2016) - Mapillary, a community-based photomapping platform, today announced the hire of Peter Kontschieder as head of a new research lab located in Graz, Austria. The lab will focus on exploring advanced computer vision techniques that will enhance Mapillary's cutting-edge image recognition technology.

"Graz has a thriving cluster of artificial intelligence research and talent, so it was a natural choice for us," said Jan Erik Solem, CEO of Mapillary. "We are excited to have Peter lead our deep learning team, and we will grow the team there to further improve our ability to extract useful data from images."

The new research lab's efforts will focus on leveraging Mapillary's more than 61 million photos in order to improve the ability of machines to analyze images. Mapillary is particularly well-suited for this research because of its active community. In order to train a machine to recognize items in images, researchers need examples of photos in which key objects like street signs and people have been tagged. The more annotated photos machines have to process, the sharper their recognition skills will become. Mapillary's members contribute to this process by helping annotate uploaded images, and in turn will get customized recognition capabilities tailored to their interests and problems.

"I'm excited to further our research in computer vision and deep learning with Mapillary because our work will directly impact Mapillary's community and customers," said Kontschieder, who joined Mapillary from Microsoft Research, where his team won the Marr Prize last year for their paper "Deep Neural Decision Forests" that proved a new technique for teaching computers to recognize images. Kontschieder will be joined at Mapillary's new research lab by Gerhard Neuhold, a computer vision engineer formerly at Microsoft Research who previously worked on both recognition algorithms and on building street view camera rigs.

Mapillary currently provides photos and data for maps of cities, landscapes, and uncharted territories. With about 1.5 million kilometers mapped with photos, Mapillary's database is used by open data communities and city governments around the world, as well as by international nonprofits like the Red Cross and the World Bank.

Kontschieder most recently served as the lead machine learning researcher for project ASSESS MS, a collaborative effort of Microsoft Research, Novartis Pharmaceuticals, and several European university hospitals to automate disease progression quantification in multiple sclerosis patients. He received his MSc and PhD from Graz University of Technology in Austria.

Mapillary is a community-based photomapping service that covers more than just streets, providing real-time data for cities and governments at scale. With hundreds of thousands of new photos every day, Mapillary can connect images to create an immersive ground-level view of the world for users to virtually explore and to document change over time.