Intelligent Perceptual Interfaces

1
Intelligent Perceptual Interfaces

• Trevor Darrell
• Eric Grimson

2
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

3
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 its being observed
• Recognizes returning observers
• Tracks head pose
• Recognizes speech without attached microphone
• Robust to changing lighting, moving backgrounds

4
Head Pose Estimation

• Estimate gaze angle of users head
• Rigid body model 6 DOF

5
Fast and Efficient to Solve!
6
Lip Contour Tracking
Conventional
Intelligent shape tracking
7
Lip Contour Tracking - Video
8
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

9
Audio-based Image Localization

• Can we locate visual sources given audio
  information?

Original Sequence
10
Audio-based Image Localization

• Image variance (ignoring audio) will find all
  motion in the sequence

Image Variance
11
Audio-based Image Localization

• Examine Mutual Information (Correlation in
  simplest case) between image and audio

Pixels with high mutual information with audio
track
12
Learning an Informative Subspace
Learned Subspace
video projection
audio projection
Find a projection of both the video data and the
audio data to a low-dimensional space so that MI
is maximized.