UCSD Student Solve Google Street View's Privacy Problem

A computer science student at the University of California San Diego developed a software to remove objects from Google's Street View. "The original goal was to remove foreground objects in general. This would allow a completely unobstructed view of the background. This proved to be too difficult, so a way to make it easier to […]

A computer science student at the University of California San Diego developed a software to remove objects from Google's Street View. "The original goal was to remove foreground objects in general. This would allow a completely unobstructed view of the background. This proved to be too difficult, so a way to make it easier to manage was to focus on only removing pedestrians and focusing on the privacy issue," Arturo Flores said in an email.

Flores, and Serge Belongie, his professor, have published their findings (1.7mb PDF) in a research paper called "Removing pedestrians from Google Street View images." The paper explains in detail how their software creates "ghost-free mosaics" by matching redundant pixels from different photos of the same location "to remove the pedestrian as if it had never been there."

Refrence: IWMV Research Paper

[Source]