Duke researchers have developed a smartphone application that creates fingerprints of an interior space’s ambience, which might be the answer to GPS’s weaknesses. "We believe that SurroundSense is an early step toward a long-standing challenge of improving indoor localization," Duke assistant professor of electrical and computer engineering Roy Choudhury said. (Choudhury is also the head of another cool project we wrote about a few months back.) SurroundSense takes a sound and light fingerprint from the space a user is in and compares it against a database of locations, using a smartphone’s camera and microphone to record information about the space.
The phone’s accelerometer traces its user’s movement patterns within that space, as the way people move in different establishments (sitting for long periods at a restaurant vs. walking quickly up and down aisles in grocery stores, for example) as distinguishing traffic patterns for a given store at given times of the day.
This could be a workaround for GPS, which does not function indoors, and is only accurate down to 32 feet.
SurroundSense depends on its database to ensure the accuracy of its fingerprints, a database that will grow as users continue to use the app.
"As the system collects and analyzes more and more information about a particular site, the fingerprint becomes that much more precise," said Roy Choudhury. "Not only is the ambience different at different locations, but also can be different at different times at the same location."
"You can't tell much from any of the measurements individually, but when combined, the optical, acoustic and motion information creates a unique fingerprint of the space," said Ionut Constandache, a Duke computer science student and member of the team.
Still early in its development phase, SurroundSense was able to correctly identify 87 percent of the 51 spaces it has been tested in.
While most of the potential uses proposed so far are for location-specific – you guessed it – advertising, more interesting uses are also being theorized, such as using SurroundSense as tool to aid the visually impaired navigate large indoor spaces such as malls.
SurroundSense was presented September 25th at the 15th International Conference on Mobile Computing and Networking in Bejing.