computer vision (cse p576)
DESCRIPTION
Computer Vision (CSE P576). Staff Prof: Steve Seitz ( seitz@cs ) TA: Jiun-Hung Chen ( jhchen@cs ) Web Page http://www.cs.washington.edu/education/courses/csep576/05wi/ Handouts signup sheet intro slides image filtering slides image sampling slides. Today. Intros - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/1.jpg)
Computer Vision (CSE P576)
Staff• Prof: Steve Seitz (seitz@cs )• TA: Jiun-Hung Chen (jhchen@cs)
Web Page• http://www.cs.washington.edu/education/courses/csep576/05wi/
Handouts• signup sheet• intro slides• image filtering slides• image sampling slides
![Page 2: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/2.jpg)
Today• Intros• Computer vision overview• Course overview• Image processing
Readings for this week• Forsyth & Ponce textbook, chapter 7
![Page 3: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/3.jpg)
Every picture tells a story
Goal of computer vision is to write computer programs that can interpret images
![Page 4: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/4.jpg)
Can computers match human perception?
Yes and no (but mostly no!)• humans are much better at “hard” things• computers can be better at “easy” things
![Page 5: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/5.jpg)
Perception
![Page 6: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/6.jpg)
Perception
![Page 7: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/7.jpg)
Perception
![Page 8: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/8.jpg)
Low level processing
Low level operations• Image enhancement, feature detection, region segmentation
![Page 9: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/9.jpg)
Mid level processing
Mid level operations• 3D shape reconstruction, motion estimation
![Page 10: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/10.jpg)
High level processing
High level operations• Recognition of people, places, events
![Page 11: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/11.jpg)
Image Enhancement
Image Inpainting, M. Bertalmío et al.http://www.iua.upf.es/~mbertalmio//restoration.html
![Page 12: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/12.jpg)
Image Enhancement
Image Inpainting, M. Bertalmío et al.http://www.iua.upf.es/~mbertalmio//restoration.html
![Page 13: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/13.jpg)
Image Enhancement
Image Inpainting, M. Bertalmío et al.http://www.iua.upf.es/~mbertalmio//restoration.html
![Page 14: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/14.jpg)
Application: Document Analysis
Digit recognition, AT&T labshttp://www.research.att.com/~yann/
![Page 15: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/15.jpg)
Applications: 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
![Page 16: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/16.jpg)
The Digital Michelangelo Project, Levoy et al.
![Page 17: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/17.jpg)
![Page 18: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/18.jpg)
![Page 19: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/19.jpg)
![Page 20: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/20.jpg)
![Page 21: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/21.jpg)
![Page 22: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/22.jpg)
ESC Entertainment, XYZRGB, NRC
![Page 23: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/23.jpg)
Applications: Motion Capture, Games
![Page 24: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/24.jpg)
Andy Serkis, Gollum, Lord of the Rings
![Page 25: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/25.jpg)
Application: Medical Imaging
![Page 26: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/26.jpg)
Applications: Robotics
![Page 27: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/27.jpg)
SyllabusImage Processing (2 weeks)• filtering, convolution • image pyramids • edge detection • feature detection (corners, lines) • hough transform
Image Transformation (2 weeks)• image warping (parametric transformations, texture mapping) • image compositing (alpha blending, color mosaics) • segmentation and matting (snakes, scissors)
Motion Estimation (1 week)• optical flow • image alignment • image mosaics • feature tracking
![Page 28: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/28.jpg)
SyllabusLight (1 week)• physics of light • color • reflection • shading • shape from shading • photometric stereo
3D Modeling (3 weeks)• projective geometry • camera modeling • single view metrology • camera calibration • stereo
Object Recognition and Applications (1 week)• eigenfaces • applications (graphics, robotics)
![Page 29: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/29.jpg)
Project 1: Intelligent Scissors
![Page 30: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/30.jpg)
Project 2: Panorama Stitchinghttp://www.cs.washington.edu/education/courses/455/03wi/projects/project2/artifacts/crosetti/index.shtml
![Page 31: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/31.jpg)
Project 3: 3D Shape Reconstruction
![Page 32: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/32.jpg)
Project 4: Face Recognition
![Page 33: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/33.jpg)
Class Webpagehttp://www.cs.washington.edu/education/courses/csep576/05wi/
![Page 34: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/34.jpg)
Grading
Programming Projects (100%)• image scissors• panoramas• 3D shape modeling• face recognition
![Page 35: Computer Vision (CSE P576)](https://reader035.vdocuments.site/reader035/viewer/2022062217/56812e44550346895d93d0b8/html5/thumbnails/35.jpg)
General CommentsPrerequisites—these are essential!
• Data structures• A good working knowledge of C and C++ programming
– (or willingness/time to pick it up quickly!)
• Linear algebra • Vector calculus
Course does not assume prior imaging experience• computer vision, image processing, graphics, etc.