Want to blend in? New algorithms produces instant-camouflage

Bookmark and Share

If a bulky electrical box has to be placed at the edge of a public park, what’s the best way to conceal it so that it won’t detract from its surroundings? How about an air-conditioning condenser beside a historical building, or a portable toilet along a scenic trail?

At the conference on Computer Vision and Pattern Recognition in June, researchers from CSAIL and several other institutions take a first stab at answering these types of questions, with a new algorithm that can analyze photos of a scene, taken from multiple perspectives, and produce a camouflage covering for an object placed within it.

Objects hidden by the team's best-performing algorithm took, on average, more than three seconds to find — significantly longer than the casual glance the camouflage is intended to thwart.

The recent paper was written by CSAIL graduate student Andrew Owens, alongside CSAIL researcher (and MIT professor) William Freeman and collaborators from the University of Virginia, Flyby Media and the Woods Hole Oceanographic Institution.