United States modelling group URC ventures, in partnership with the University of North Carolina Department of Computer Science, has developed a 3D reconstruction method using computer vision and 3D modelling techniques to turn publicly available photos into functional 3D models. Using Yahoo’s publically available collection of 100 million crowd-sourced photos and photogrammetry, the team created a new software process able to automatically construct 12,903 3D models in just six days.
Jared Heinly, Johannes L. Schönberger, Enrique Dunn and Jan-Michael Frahm of UNC’s 3D Computer Vision Group have created software that processes world-scale datasets to create 3D models and visualisations of locations all over the world, including Notre Dame, the Roman Pantheon, and Sydney’s Luna Park.
David Boardman, the CEO of URCV pointed out the potential commercial applications of this sort of process: “Reconstructing the world’s landmarks so quickly is only one example of social application, pointing the way towards many future possibilities.”
URCV also uses the technology for their stockpile management system Stockpile Reports which transforms iPhone imagery into inventory measurement.
“Imagine imagery streaming in from UAV, planes, cell phones, truck mounted cameras, and hard hat cameras enabling the reconstruction of mining and construction operations at any point in time,” said Boardman.
“Or imagine imagery from the millions of self-driving cars in the future being leveraged to create up-to-the-second street maps. Think of the lives that would be saved if First Responders could see an up-to-the-minute model of an emergency scene before arriving.”
For more information visit the URCV website.