Dr. Srihari Nelakuditi, along with Dr. Romit Roy Choudhury at Duke University, is a recipient of the prestigious Google Faculty Research Award for their project titled "Google Glass meets Smartphones: Recognizing Humans without Face Recognition" which proposes to identify individuals based on their clothes and motion patterns when seen via Google Glass. This New Scientist article describes their research, and has been picked up by many media outlets and USC News. See video.
You can also listen to an interview of Dr. Nelakuditi at the IT minute podcast.
This project explores techniques that jointly leverage Google Glass and smartphones to automatically recognize people in the visual surrounding. This enables a scenario where Alice can look at any other person around her, say Bob, and view his Google+ profile. While face recognition would be one approach to this problem, we believe that it may not be always possible to see a person’s face. Our technique is complementary to face recognition, and exploits the intuition that colors and decorations of clothes, and even human motion patterns, can together make up a “fingerprint” that helps recognize the person. This project is expected to not only facilitate human recognition, but also provide a useful primitive for human-centric augmented reality.