Researchers build what they describe as a ”dynamic version” of Google Street View by combining millions of images and videos into a three-dimensional, living model of the city of Zurich. Reuters’ Matthew Stock reports.
By scouring the internet for images and videos, a smart algorithm built this 3D model of Zurich.
The platform – called VarCity – updates in real-time when new images are found. Effectively, creating a ‘living’, ‘evolving’ 3D model of the city.
“Aerial data, drone data, static webcams, and publicly available Flickr images. And we’ve fused all of this information into one coherent 3D model, and we can add new and additional images all the time,” Hyko Riemenschneider, post doctoral research at Eth Zurich/Varcity project manager, saying.
Their learning algorithm finds correspondences between pixels and images, using triangulation to build a point-cloud and create a precise 3D model.
“In this project we’ve built a 3D model of Zurich city by exploiting 4 terabytes of images – that’s 3 million images. And by using the knowledge we automatically deduce in this project from this data we can build a compressed 3D model that can then be used to walk through in real time, just like in a virtual game, for example,” Kenneth Vanhoey, post doctoral research at Eth Zurich, saying.
Programs like Google Street View give users a similar experience. But VarCity’s developers say their platform is enriched with far more useful data.
“In comparison to Google Street View, we’re trying to make a dynamic version which is augmented with knowledge…. we use artificial intelligence to understand every part of the building, so we know where windows, doors and balconies are, and where pedestrians and cars are. And we can augment the city with this additional knowledge,” Riemenschneider, saying.
Such knowledge, they say, could improve the city’s infrastructure on a daily basis. The team from ETH Zurich has founded several spin-off companies to use the VarCity platform. These include providing virtual damage analyses on buildings for insurance companies, and real-time traffic monitoring.
