David Martin
David Martin received his Bachelor of Science & Engineering summa cum laude in Computer Science from Princeton University in 1996 and his Ph.D. in Computer Science from U.C. Berkeley in 2003 with primary focus in computer vision and secondary focus in computer architecture and parallel computing. From 2003-2009, he was an Assistant Professor in the Computer Science Department at Boston College. He joined the Street View Team at Google in 2009 and works on problems in image processing, machine vision, and large scale optimization.
Research Areas
Authored Publications
Google Publications
Other Publications
Sort By
Street View Motion-from-Structure-from-Motion
James Roseborough
Proceedings of the International Conference on Computer Vision, IEEE (2013)
Preview abstract
We describe a structure-from-motion framework that handles "generalized" cameras, such as moving rolling-shutter cameras, and works at an unprecedented scale--billions of images covering millions of linear kilometers of roads--by exploiting a good relative pose prior along vehicle paths. We exhibit a planet-scale, appearance-augmented point cloud constructed with our framework and demonstrate its practical use in correcting the pose of a street-level image collection.
View details
No Results Found