MIT Artificial Intelligence Laboratory — Research Directions Intelligent Perceptual Interfaces Trevor Darrell Eric Grimson
MIT Artificial Intelligence Laboratory — Research Directions Perceptual User Interfaces Interactivity- be aware of viewer! People have natural interface modes Watch, listen, learn signals from user Key concepts: –Transparency - embedded interfaces –Expressiveness - balance interface I/O bandwidth Key technologies: –Computer Vision –Machine Learning –Spoken Language Understanding
MIT Artificial Intelligence Laboratory — Research Directions A Face Responsive Display Faces are natural interfaces! –Ubiquitous, fast, expressive, general. –Want machines to generate and perceive faces. A Face Responsive Display... –Knows when it’s being observed –Recognizes returning observers –Tracks head pose –Recognizes speech without attached microphone –Robust to changing lighting, moving backgrounds…
MIT Artificial Intelligence Laboratory — Research Directions Head Pose Estimation Estimate gaze angle of user’s head Rigid body model: 6 DOF
MIT Artificial Intelligence Laboratory — Research Directions Fast and Efficient to Solve!
MIT Artificial Intelligence Laboratory — Research Directions Lip Contour Tracking Conventional Intelligent shape tracking
MIT Artificial Intelligence Laboratory — Research Directions Lip Contour Tracking - Video
MIT Artificial Intelligence Laboratory — Research Directions Untethered Audio-Visual Interface Current audio interfaces often require attached microphone — future systems need wireless interface Common approaches –Beam-forming microphone –Active narrow-field microphone New idea — exploit joint statistics of audio and visual information Correlation / mutual information between audio and image pixels can separate sources
MIT Artificial Intelligence Laboratory — Research Directions Audio-based Image Localization Can we locate visual sources given audio information? Original Sequence
MIT Artificial Intelligence Laboratory — Research Directions Audio-based Image Localization Image variance (ignoring audio) will find all motion in the sequence: Image Variance
MIT Artificial Intelligence Laboratory — Research Directions Audio-based Image Localization Examine Mutual Information (Correlation in simplest case) between image and audio: Pixels with high mutual information with audio track
MIT Artificial Intelligence Laboratory — Research Directions Learning an Informative Subspace Learned Subspace audio projection video projection Find a projection of both the video data and the audio data to a low- dimensional space so that MI is maximized.