Transcript Kein Folientitel - University of California, Berkeley

The Hilbert Problems of Computer Vision
Jitendra Malik
University of California
Berkeley
Computer Vision Group
Forty years of computer vision 1963-2003
• 1960s: Beginnings in artificial intelligence, image
processing and pattern recognition
• 1970s: Foundational work on image formation: Horn,
Koenderink, Longuet-Higgins …
• 1980s: Vision as applied mathematics: geometry,
multi-scale analysis, control theory, optimization …
• 1990s:
– Geometric analysis largely completed
– Probabilistic/Learning approaches in full swing
– Successful applications in graphics, biometrics, HCI …
University of California
Berkeley
Computer Vision Group
And now …
• Back to basics: the classic problem of
understanding the scene from its image/s
• Central question: Interplay of bottom-up and
top-down information
University of California
Berkeley
Computer Vision Group
Early Vision
• What can we learn from image statistics that
we didn't know already?
• How far can bottom-up image segmentation
go?
• How do we make inferences from shading and
texture patterns in natural images?
University of California
Berkeley
Computer Vision Group
Static Scene Understanding
• What is the interaction between segmentation
and recognition?
• What is the interaction between scenes, objects,
and parts?
• What is the role of design vs. learning in
recognition systems?
University of California
Berkeley
Computer Vision Group
Dynamic Scene Understanding
• What is the role of high-level knowledge in
long range motion correspondence?
• How do we find and track articulated
structures?
• How do we represent "movemes" and actions?
University of California
Berkeley
Computer Vision Group
From Images to Objects
"I stand at the window and see a house, trees, sky. Theoretically I
might say there were 327 brightnesses and nuances of colour. Do
I have "327"? No. I have sky, house, and trees." --Max Wertheimer
University of California
Berkeley
Computer Vision Group