12 August 2014

Sound for Indoor Localization

The global positioning system, or GPS, has its limitation (i.e. it cannot work indoors). Potential solutions for indoor positioning continue to fire up the imaginations of scientists. The latest news involves a form of echolocation. MIT Technology Review reported on the approach for indoor localization based on sound. Researchers at the University of California, Berkeley developed a simple, cheap mechanism that can identify rooms based on a relatively small dataset. Their method is based on the extraction of acoustic features of rooms. The team said they can acquire RIRs (room impulse responses) by using built-in speakers and microphones on laptops.


Also, a noise adaptive reverberation extraction algorithm was developed for feature extraction from the noisy RIRs. The researchers tested their system in ten rooms on the Berkeley campus. Data was taken using the built-in microphone and speakers on an ordinary laptop. The laptop produces a set of sound waves and then listens for the echo. They took 50 samples at each location, which included background noise such as footsteps, talking and heating and ventilation sounds. They processed this data to find the echo fingerprint for each room. The team said there was a 97.8 percent accuracy in identifying the individual rooms.

More information: