1 / 38

Introduction

Introduction. Vision. ``to know what is where, by looking.’’ (Marr). Where What. What is Computer Vision?. Vision is about discovering from images what is present in the scene and where it is.

vsilverman
Télécharger la présentation

Introduction

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Introduction Computer Vision

  2. Vision • ``to know what is where, by looking.’’ (Marr). • Where • What Computer Vision

  3. What is Computer Vision? Computer Vision Vision is about discovering from images what is present in the scene and where it is. In Computer Vision a camera (or several cameras) is linked to a computer. The computer interprets images of a real scene to obtain information useful for tasks such as navigation, manipulation and recognition.

  4. Applications Intelligent machines (AI) Industrial inspection e.g. light bulbs, electronic circuits Automotive e.g. Ford, GM, DARPA Grand Challenge Security e.g. facial recognition in airports Toys (Aibo dog) Image/video retrieval Digital cameras are everywhere now…. Computer Vision

  5. Vision is inferential: Light (http://www-bcs.mit.edu/people/adelson/checkershadow_illusion.html) Computer Vision

  6. Vision is Inferential: Prior Knowledge Computer Vision

  7. Computer Vision • Inference  Computation • Building machines that see • Modeling biological perception Computer Vision

  8. The Human Eye Computer Vision Retina measures about 5 × 5 cm and contains 108 sampling elements (rods and cones). The eye’s spatial resolution is about 0.01◦ over a 150◦ field of view (not evenly spaced, there is a fovea and a peripheral region). Intensity resolution is about 11 bits/element, spectral range is 400–700nm. Temporal resolution is about 100 ms (10 Hz). Two eyes give a data rate of about 3 GBytes/s!

  9. Human visual system • Vision is the most powerful of our own senses. [Thorpe et. al.] • Around 1/3 of our brain is devoted to processing the signals from our eyes. • The visual cortex has around O(1011) neurons. Computer Vision

  10. 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. Computer Vision

  11. Computer Vision: A whole series of problems • What is in the image ? • - Object recognition problem • Where is it ? • - 3D spatial layout • Shape • How is the camera moving ? • What is the action ? Computer Vision

  12. A Quick Tour of Computer Vision Computer Vision

  13. Boundary Detection http://www.robots.ox.ac.uk/~vdg/dynamics.html Computer Vision

  14. Computer Vision

  15. Boundary Detection Finding the Corpus Callosum (G. Hamarneh, T. McInerney, D. Terzopoulos) Computer Vision

  16. Tracking Computer Vision

  17. Tracking Computer Vision

  18. Tracking Computer Vision

  19. Tracking Computer Vision

  20. Tracking Computer Vision

  21. Application: Assisted driving meters Ped Ped Car meters Pedestrian and car detection Lane detection • Collision warning systems with adaptive cruise control, • Lane departure warning systems, • Rear object detection systems, Computer Vision

  22. Stereo Computer Vision

  23. Stereo http://www.magiceye.com/ Computer Vision

  24. Motion http://www.ai.mit.edu/courses/6.801/lect/lect01_darrell.pdf Computer Vision

  25. Motion - Application (www.realviz.com) Computer Vision

  26. Pose Determination Visually guided surgery Computer Vision

  27. Recognition - Shading Lighting affects appearance Computer Vision

  28. Computer Vision

  29. Classification (Funkhauser, Min, Kazhdan, Chen, Halderman, Dobkin, Jacobs) Computer Vision

  30. Application: Improving online search Query: STREET Organizing photo collections Computer Vision

  31. Vision depends on: • Geometry • Physics • The nature of objects in the world (This is the hardest part). Computer Vision

  32. Approaches to Vision Computer Vision

  33. 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. Computer Vision

  34. 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. Computer Vision

  35. 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. Computer Vision

  36. 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. Computer Vision

  37. The State of Computer Vision • Technology • Interesting applications: inspection, graphics, security, internet…. • Some successful companies. Largest ~100-200 million in revenues. Many in-house applications. • Future: growth in digital images exciting. Computer Vision

  38. Related Fields • Graphics. “Vision is inverse graphics”. • Visual perception. • Neuroscience. • AI • Learning • Math: eg., geometry, stochastic processes. • Optimization. Computer Vision

More Related