Using math and crowdsourcing to camouflage ‘eyesores’

MIT researchers look for method to cover up electrical boxes and the like

Researchers at MIT are leading an effort to use algorithms and crowdsourcing to create customized camouflage that someday will conceal public eyesores such as electrical boxes and air conditioning units.

Among the challenges to be overcome is creating camouflage that does the trick when viewed from different vantage points and in different light conditions.

In a second you'll see some examples and even get to participate in the crowdsourcing effort.

First, from an MIT press release:

The researchers developed a range of candidate algorithms and tested them using Amazon's Mechanical Turk crowdsourcing application, scoring them according to the amount of time volunteers took to locate camouflaged objects in synthetic images. Objects hidden by their best-performing algorithm took, on average, more than three seconds to find - significantly longer than the casual glance the camouflage is intended to thwart.

According to Andrew Owens, an MIT graduate student in electrical engineering and computer science and lead author on the new paper, the problem of disguising objects in a scene is, to some degree, the inverse of the problem of object detection, a major area of research in computer vision.

"Often these algorithms work by searching for specific cues - for example they might look for the contours of the object, or for distinctive textures." Owens says. "With camouflage, you want to avoid these cues - you don't want the object's contours to be visible or for its texture to be very distinctive. Conceptually, a cue that would be good for detecting an object is something that you want to remove."

This video shows various demonstrations, though the crowdsourcing app that follows seems to illustrate the concept more clearly.

But perhaps more enlightening than the video is this "camouflage game" that invites us "to find the hidden box."

The first scenes are intended to be relatively easy warm-ups, including:

Test 11
Test 22

And then there are scenes where the box is more difficult to find, such as here:

Test 33
Test 44

I fared reasonably well, but there were more than a few where I ran out of time before spotting anything suspicious enough to click on.

A paper on the research can be found here (.pdf). And here is the project's website.

This one's not a time waster, so go ahead and give it a try ... for science.  

Join the Network World communities on Facebook and LinkedIn to comment on topics that are top of mind.
Must read: 10 new UI features coming to Windows 10