© 2004 by Davi GeigerComputer Vision January 2004 L1.1 Introduction

© 2004 by Davi GeigerComputer Vision January 2004 L1.2 Vision ``to know what is where, by looking.’’ (Marr). Where What

© 2004 by Davi GeigerComputer Vision January 2004 L1.3 Why is Vision Interesting? Psychology –~ 35% of cerebral cortex is for vision. –Vision is how we experience the world. Engineering –Want machines to interact with world. –Digital images are everywhere.

© 2004 by Davi GeigerComputer Vision January 2004 L1.4 Vision is inferential: Light (

© 2004 by Davi GeigerComputer Vision January 2004 L1.5 Vision is Inferential: Prior Knowledge

© 2004 by Davi GeigerComputer Vision January 2004 L1.6

© 2004 by Davi GeigerComputer Vision January 2004 L1.7 Computer Vision Inference  Computation Building machines that see Modeling biological perception

© 2004 by Davi GeigerComputer Vision January 2004 L1.8 A Quick Tour of Computer Vision

© 2004 by Davi GeigerComputer Vision January 2004 L1.9 Boundary Detection

© 2004 by Davi GeigerComputer Vision January 2004 L1.10

© 2004 by Davi GeigerComputer Vision January 2004 L1.11 Boundary Detection Finding the Corpus Callosum (G. Hamarneh, T. McInerney, D. Terzopoulos)

© 2004 by Davi GeigerComputer Vision January 2004 L1.12 Tracking

© 2004 by Davi GeigerComputer Vision January 2004 L1.13 Tracking

© 2004 by Davi GeigerComputer Vision January 2004 L1.14 Tracking

© 2004 by Davi GeigerComputer Vision January 2004 L1.15 Tracking

© 2004 by Davi GeigerComputer Vision January 2004 L1.16 Tracking

© 2004 by Davi GeigerComputer Vision January 2004 L1.17 Stereo

© 2004 by Davi GeigerComputer Vision January 2004 L1.18 Stereo

© 2004 by Davi GeigerComputer Vision January 2004 L1.19 Motion

© 2004 by Davi GeigerComputer Vision January 2004 L1.20 Motion - Application (

© 2004 by Davi GeigerComputer Vision January 2004 L1.21 Pose Determination Visually guided surgery

© 2004 by Davi GeigerComputer Vision January 2004 L1.22 Recognition - Shading Lighting affects appearance

© 2004 by Davi GeigerComputer Vision January 2004 L1.23 Classification (Funkhauser, Min, Kazhdan, Chen, Halderman, Dobkin, Jacobs)

© 2004 by Davi GeigerComputer Vision January 2004 L1.24 Vision depends on: Geometry Physics The nature of objects in the world (This is the hardest part).

© 2004 by Davi GeigerComputer Vision January 2004 L1.25 Approaches to Vision

© 2004 by Davi GeigerComputer Vision January 2004 L1.26 Modeling + Algorithms Build a simple model of the world (eg., flat, uniform intensity). Find provably good algorithms. Experiment on real world. Update model. Problem: Too often models are simplistic or intractable.

© 2004 by Davi GeigerComputer Vision January 2004 L1.27 Bayesian inference Bayes law: P(A|B) = P(B|A)*P(A)/P(B). P(world|image) = P(image|world)*P(world)/P(image) P(image|world) is computer graphics –Geometry of projection. –Physics of light and reflection. P(world) means modeling objects in world. Leads to statistical/learning approaches. Problem: Too often probabilities can’t be known and are invented.

© 2004 by Davi GeigerComputer Vision January 2004 L1.28 Engineering Focus on definite tasks with clear requirements. Try ideas based on theory and get experience about what works. Try to build reusable modules. Problem: Solutions that work under specific conditions may not generalize.

© 2004 by Davi GeigerComputer Vision January 2004 L1.29 Marr Theory of Computation Representations and algorithms Implementations. Primal Sketch 2½D Sketch 3D Representations Problem: Are things really so modular?

© 2004 by Davi GeigerComputer Vision January 2004 L1.30 The State of Computer Vision Science –Study of intelligence seems to be hard. –Some interesting fundamental theory about specific problems. –Limited insight into how these interact.

© 2004 by Davi GeigerComputer Vision January 2004 L1.31 The State of Computer Vision Technology –Interesting applications: inspection, graphics, security, internet…. –Some successful companies. Largest ~ million in revenues. Many in- house applications. –Future: growth in digital images exciting.

© 2004 by Davi GeigerComputer Vision January 2004 L1.32 Related Fields Graphics. “Vision is inverse graphics”. Visual perception. Neuroscience. AI Learning Math: eg., geometry, stochastic processes. Optimization.