Download
computational vision n.
Skip this Video
Loading SlideShow in 5 Seconds..
Computational Vision PowerPoint Presentation
Download Presentation
Computational Vision

Computational Vision

97 Vues Download Presentation
Télécharger la présentation

Computational Vision

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Computational Vision Jitendra Malik University of California at Berkeley

  2. 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.

  3. 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.

  4. 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.

  5. Arc de Triomphe

  6. Taj Mahal modeled from one photograph by G. Borshukov

  7. Recovered Campus Model Campanile + 40 Buildings (Debevec et al)

  8. Inverse Global Illumination (Yu et al) Reflectance Properties Radiance Maps Light Sources Geometry

  9. Real vs. Synthetic

  10. Real vs. Synthetic

  11. 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

  12. 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

  13. 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

  14. Image Segmentation

  15. Boundaries of image regions defined by a number of attributes • Brightness/color • Texture • Motion • Stereoscopic depth • Familiar configuration

  16. 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

  17. Image Segmentation as Graph Partitioning Build a weighted graph G=(V,E) from image V: image pixels E: connections between pairs of nearby pixels Partition graph so that similarity within group is large and similarity between groups is small -- Normalized Cuts [Shi&Malik 97]

  18. Temporal Segmentation: Tracking

  19. Challenges in Segmentation • Interaction of multiple cues • Local measurements to global percepts • Interplay of image-driven and object model driven processing

  20. 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

  21. Recognition of Gait and Gesture run measurement recognition animation

  22. Challenges in recognition • Unified framework for segmentation and recognition • Representing shape variability in a category • Interplay of discriminative vs generative models

  23. Core disciplines • Geometry • Differential geometry • Projective geometry • Probability and Statistics • Reconstruction = estimation • Control = decision theory • Segmentation = clustering • Recognition = classification