01 cie552 introduction
•Download as PPTX, PDF•
0 likes•50 views
Introduction to computer vision
Recommended
More Related Content
What's hot
What's hot (20)
Similar to 01 cie552 introduction
Similar to 01 cie552 introduction (20)
More from Elsayed Hemayed
More from Elsayed Hemayed (20)
Recently uploaded
Recently uploaded (20)
01 cie552 introduction
- 1. INTRODUCTION TO COMPUTER VISION Elsayed Hemayed
- 2. Welcome to Computer Vision 2
- 3. What is Computer Vision? 3 Image (or video) Sensing device Interpreting device Interpretations Road, Car, House, Grass, etc. Image Processing and Computer Vision
- 4. The Goal of Computer Vision 4 To bridge the gap between pixels and “meaning” What we see What a computer sees Image Processing and Computer Vision
- 5. 5
- 6. White 1m Shado w Car Horse Wheel Person Sky Road The car is in front of the pole 6
- 7. Computer Vision Low Level Vision Measurements Enhancements Region segmentation Features Mid Level Vision Reconstruction Depth Motion Estimation High Level Vision Category detection Activity recognition Deep understandings 7
- 8. Computer Vision Low Level Vision Measurements Enhancements Region segmentation Features Mid Level Vision Reconstruction Depth Motion Estimation High Level Vision Category detection Activity recognition Deep understandings 1m White Shado w 8
- 9. Computer Vision Low Level Vision Measurements Enhancements Region segmentation Features Mid Level Vision Reconstruction Depth Motion Estimation High Level Vision Category detection Activity recognition Deep understandings The car is in front of the pole 9
- 10. Computer Vision Low Level Vision Measurements Enhancements Region segmentation Features Mid Level Vision Reconstruction Depth Motion Estimation High Level Vision Category detection Activity recognition Deep understandings Pose estimation Car Horse PersonSky Road 10
- 11. What is A Computer Vision System?11 • One Image • Multiple Images • Video Image Enhancement Image/Video PreAnalysis • Noise removal • Contrast Enhancement • Image Normalization • Edge detection • Image segmentation • Image matching Acquisition Image/Video Analysis • Countless Applications Applications • Image retrieval • Face detection • Face Tracking • Face recognition • Object recognition • Event recognition • Video summarization • Humane Activity Rec • Navigation • Inspection • Robot Control Image Processing and Computer Vision
- 12. salt and pepper (impulse) noise Noise contamination is often inevitable during the acquisition additive white Gaussian noise Noise Removal 12 Image Processing and Computer Vision
- 13. overly-exposed image under-exposed image Contrast Enhancement 13 Image Processing and Computer Vision
- 14. “Rice” image Edges detected using Canny filter Edge Detection 14 Image Processing and Computer Vision
- 16. Image Matching 16 Image Processing and Computer Vision Fingerprint scanners on many new laptops, other devices
- 17. Reading license plates, zip codes, checks Svetlana Lazebnik Optical Character Recognition (OCR)17
- 18. retrieved building images Content-based Image Retrieval 18 Image Processing and Computer Vision
- 19. http://www-2.cs.cmu.edu/~har/faces.html Face Detection and Tracking 19 Image Processing and Computer Vision Many digital cameras now detect faces
- 20. Surveillance video Search in the database Face Recognition 20 Image Processing and Computer Vision Face recognition systems are now more widely http://www.sensiblevision.com/
- 21. Face recognition: Apple iPhoto, Facebook, Google, etc 21
- 22. Smile detection Sony Cyber-shot® T70 Digital Still Camera Source: S. Seitz 22
- 23. License number can be automatically extracted from the image of license plate Object Recognition 23 Image Processing and Computer Vision
- 24. Mobile visual search: Google Goggles24
- 25. Object recognition (in supermarkets) LaneHawk by EvolutionRobotics “A smart camera is flush-mounted in the checkout lane, continuously watching for items. When an item is detected and recognized, the cashier verifies the quantity of items that were found under the basket, and continues to close the transaction. The item can remain under the basket, and with LaneHawk,you are assured to get paid for it… “ 25
- 26. Object Recognition in Military Applications 26
- 28. Image-based monitoring system prevents drowning Event Recognition 28 Image Processing and Computer Vision
- 29. Only send out “important” motion pictures such as home-runs Video Summarization Image Processing and Computer Vision
- 30. Automotive safety Mobileye: Vision systems in high-end BMW, GM, Volvo models Pedestrian collision warning Forward collision warning Lane departure warning Headway monitoring and warning Source: A. Shashua, S. Seitz 30
- 31. Google cars Oct 9, 2010. "Google Cars Drive Themselves, in Traffic". The New York Times. John Markoff June 24, 2011. "Nevada state law paves the way for driverless cars". Financial Post. Christine Dobby Aug 9, 2011, "Human error blamed after Google's driverless car sparks five-vehicle crash". The Star (Toronto) 31
- 33. Special effects: shape and motion capture Source: S. Seitz 33
- 34. Medical imaging Image guided surgery Grimson et al., MIT 3D imaging MRI, CT 34
- 35. Vision as measurement device 35 Real-time stereo from NASA Mars Rover Pollefeys et al. Image Processing and Computer Vision
- 36. Vision for robotics, space exploration Vision systems (JPL) used for several tasks • Panorama stitching • 3D terrain modeling • Obstacle detection, position tracking • For more, read “Computer Vision on Mars” by Matthies et al. NASA'S Mars Exploration Rover Spirit captured this westward view from atop a low plateau where Spirit spent the closing months of 2007. Source: S. Seit 36
- 37. 3D Scanning Scanning Michelangelo’s “The David” • The Digital Michelangelo Project - http://graphics.stanford.edu/projects/mich/ • UW Prof. Brian Curless, collaborator • 2 BILLION polygons, accuracy to .29mm 37
- 38. Structure from Motion 38 Pollefeys et al.Image Processing and Computer Vision
- 39. Google’s 3D Maps Structure estimation from tourist photos 39
- 41. Computer vision in the real-world 41 Very active research area. Many new applications to come. A website of computer vision industries maintained by Prof. David Lowe (UBC): http://www.cs.ubc.ca/~lowe/vision.h tml
- 42. Why is vision so hard? Ill-posed problem [Sinha and Adelson 1993] 42
- 43. Challenges 1: view point variation Michelangelo 1475-1564 slide by Fei Fei, Fergus & Torralba 43
- 44. Challenges 2: illumination slide credit: S. Ullman 44
- 45. Challenges 3: occlusion Magritte, 1957 slide by Fei Fei, Fergus & Torralba 45
- 46. Challenges 4: scale slide by Fei Fei, Fergus & Torralba 46
- 47. Challenges 5: deformation Xu, Beihong 1943slide by Fei Fei, Fergus & Torralba 47
- 48. Challenges 6: background clutter slide by Fei Fei, Fergus & Torralba 48
- 49. Challenges 7: object intra-class variation slide by Fei-Fei, Fergus & Torralba 49
- 50. Human Perception It is important to understand the characteristics and limitations of the human visual system It is important to realize that the human visual system is not well understood no objective measure exists for judging the quality of an image that corresponds to human assessment of image quality the "typical" human observer does not exist 50
- 51. Human Vision System Simultaneous contrast 51 Image & Camera
- 52. Fascinating Optical Illusions 52 Image & Camera
- 53. Interpretation Ambiguity Is it seal or donkey? Is it duck or hare? 53Image & Camera