Science

Software removes pedestrians from Google Street View

Software removes pedestrians f...
A pedestrian is removed from a Google Street View image using experimental new software
A pedestrian is removed from a Google Street View image using experimental new software
View 6 Images
A pedestrian is removed from a Google Street View image using experimental new software
1/6
A pedestrian is removed from a Google Street View image using experimental new software
A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)
2/6
A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)
A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"
3/6
A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"
A pedestrian is removed from a Google Street View image using experimental new software
4/6
A pedestrian is removed from a Google Street View image using experimental new software
A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)
5/6
A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)
A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"
6/6
A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"

Google Street View, while very useful, fascinating, and full of wonderful bloopers, does rub some privacy advocates the wrong way. Should people on public streets have a reasonable expectation of not ending up with their photo on the Internet? There’s a whole other article in that, but in any case... for all the folks who do have a problem with it, a computer science graduate student is working on a solution: software that digitally removes pedestrians from Street View images. One of the byproducts of the current version of the system is somewhat unsettling, however – areas where people were in images are sometimes marked by ghost-like shapes, or even by disembodied shoes and feet.

The as-yet-unnamed program was designed by Arturo Flores from the University of California, San Diego, as a proof-of-concept for CSE 190A, a project-based computer vision and machine learning class. While Street View does already blur faces, Flores feels that clothes, body shape, and height combined with geographical location can still be enough to make some pedestrians identifiable.

A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)
A pedestrian is removed from a Google Street View image using experimental new software (note the umbrella and feet left behind)

The system works by identifying human forms in each shot, erasing them, then filling the space in with background imagery obtained from the shots taken immediately before or after. It can be stymied, however, in cases where someone was walking in the same direction as the Street View camera car, at such a speed that they blocked the same bit of background for several shots in a row.

The system also only works in urban settings, where backgrounds are predominantly flat.

A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"
A pedestrian is removed from a Google Street View image using experimental new software, with some residual "ghosting"

Flores used the Street View pedestrian locator, designed by computer science professor Bastian Leibe from Aachen University, as a jumping-off point when creating his system. He now plans on improving his pedestrian remover so it can identify and remove not only individual pedestrians, but whole groups of people.

8 comments
Janek Nikicicz
So basically like Photoshop\'s content aware fill but automated? Cool.
Ed
That\'s going to be creepy when you view a downtown street in NYC and there\'s *NOBODY* there! Talk about Omega Man scenario!
ukatama
I checked the new look Google in New York and pedestrians are still in the streets. Some street were clear and others still had people in them.
JLR
As low resolution as the photos are on GoogleMaps, there shouldn\'t be anyone worried about privacy. Nobody there is recognizable. Unreadable license plate numbers are already fogged out. Shouldn\'t bother with this.
Will, the tink
I think anything done for privacy rights is a step in the right direction. Anytime you do not have the persons permission to take their picture then post it for the whole world to see, we have lost rights so cudos to Arturo Flores! Now perhaps we can make a game of it similar to geo-tagging where we identify ghosts in pics!
misterkenosborn
It\'s also possible to remove people, animals, or any thing moving with the current breed of HDR software that have a \'ghost\' removal feature. And, of course, it\'s always been possible to do this manually using multiple exposures, as had been done DOF (days-of-film). But that can be VERY time consuming.
misterkenosborn
It\'s also possible to remove people, animals, or any thing moving with the current breed of HDR software that have a \'ghost\' removal feature. And, of course, it\'s always been possible to do this manually using multiple exposures, as had been done DOF (days-of-film). But that can be VERY time consuming.
Stephen Potts
This app is still not available!