Say 'Servus' to Our New AI Lab!
Today we're excited to announce our recent addition to the computer vision side of Mapillary. We're opening an office and a deep learning AI lab in Graz, Austria. This is a big step in our quest of understanding places and how these places change over time based on our community's photographs.
The team specializes in object recognition and semantic segmentation, which means that objects are recognized and labels assigned to each region in the photos. We're going to deploy this globally across all 60M+ photos on Mapillary and make all of this data available to our members, OpenStreetMap, and our customers. Further on, you will also be able to access the technology and train our system to recognize objects that are important to you.
Example semantic segmentation from our initial system trained by Gerhard.
The Graz lab initially consists of Peter Kontschieder and Gerhard Neuhold, both amazing researchers with a ton of experience. Give them a warm welcome and stay tuned for more computer vision magic on Mapillary.
Peter will present some of his recent research on "Dropout Distillation" at the LDV Vision Summit in NYC next week. Here's a video of him presenting his recent award winning paper.
Come visit us in the lovely city of Graz:
/Jan Erik
Link to the official press release.