Docstoc

nas

Document Sample
nas Powered By Docstoc
					  Computational Vision

          Jitendra Malik
University of California at Berkeley
  Taxonomy of Vision Problems
• Reconstruction:
  – estimate parameters of external 3D world.
• Visual Control:
  – visually guided locomotion and manipulation.
• Segmentation:
  – partition I(x,y,t) into subsets of separate objects.
• Recognition:
  – classes: face vs. non-face,
  – activities: gesture, expression.
            Reconstruction
• Computer graphics is the forward problem:
  given scene geometry, reflectances and
  lighting, synthesize an image.
• Computer vision must address the inverse
  problem: given an image/multiple images,
  reconstruct the scene geometry, reflectacnes
  and illumination.
        Recovering geometry
• Historical roots in photogrammetry and
  analysis of 3D cues in human vision
• Single images adequate given knowledge of
  object class
• Multiple images make the problem easier,
  but not trivial as corresponding points must
  be identified.
 Arc de
Triomphe
   Taj Mahal
  modeled from
 one photograph
by G. Borshukov
  Recovered Campus Model




Campanile + 40 Buildings (Debevec et al)
Inverse Global Illumination (Yu et al)

     Reflectance         Radiance
     Properties           Maps




     Geometry              Light
                          Sources
Real vs. Synthetic
Real vs. Synthetic
  Challenges in Reconstruction
• Finding correspondences automatically
• Optimal estimation of structure from n
  views under perspective projection
• Models of reflectance and texture for
  natural materials and objects
                   Control
• Visual feedback signal for control of
  manipulation tasks such as grasping,
  moving and assembly
• Visual feedback for guiding locomotion
  – Obstacle avoidance for a moving robot
  – Lateral and longitudinal control of driving
        Challenges in control
• Delay in feedback loop due to visual
  processing
• Hierarchies in sensory motor control
  – Open loop or closed loop
  – Discrete planning or continuous control
Image Segmentation
Boundaries of image regions defined
    by a number of attributes
 –   Brightness/color
 –   Texture
 –   Motion
 –   Stereoscopic depth
 –   Familiar configuration
              Approaches
• Fitting a piecewise smooth surface to the
  image e.g. Mumford and Shah
• Probabilistic Inference using Markov
  Random Field model of image e.g. Geman
  and Geman
• Graph partitioning using spectral techniques
  e.g. Shi and Malik
Image Segmentation as Graph Partitioning
       Build a weighted graph G=(V,E) from image
                                    V: image pixels
                                    E: connections between
                                       pairs of nearby pixels
                                    Wij : probabilit y that i &j
                                         belong to the same
                                         region

Partition graph so that similarity within group is large and
similarity between groups is small -- Normalized Cuts
[Shi&Malik 97]
Temporal Segmentation: Tracking
   Challenges in Segmentation
• Interaction of multiple cues
• Local measurements to global percepts
• Interplay of image-driven and object model
  driven processing
                 Recognition




• Possible for both instances or object classes (Mona
  Lisa vs. faces or Beetle vs. cars)
• Tolerant to changes in pose and illumination, and
  occlusion
Recognition of Gait and Gesture




                     run


      measurement recognition   animation
     Challenges in recognition
• Unified framework for segmentation and
  recognition
• Representing shape variability in a category
• Interplay of discriminative vs generative
  models
              Core disciplines
• Geometry
  – Differential geometry
  – Projective geometry
• Probability and Statistics
  –   Reconstruction = estimation
  –   Control = decision theory
  –   Segmentation = clustering
  –   Recognition = classification

				
DOCUMENT INFO
Shared By:
Categories:
Stats:
views:17
posted:5/6/2011
language:English
pages:25