CS 453 - Spring 2016

Computer Vision


Announcements

Final projects

Final Exam: Self-scheduled (pick up from my office door), Wednesday 5/18 - Tuesday 5/24.

The exam is 3 hours (but you have an extra 30 minutes if you need them), open book / notes. You may use a computer only to access our online textbook and our course page, including homework, solutions, and student presentations. You may not use the computer for any other purpose, including searching the web.
You must return the exam within 4 hours after picking it up. Record sign-out and sign-in time and date on the sheet on my office door. Slide the completed exam under my office door.
All exams must be back by 5pm on Tuesday May 24. Seniors must return their exams by 5pm on Sunday, May 22.

Practice questions on epipolar geometry. Solutions.

Presentations

Homework

  1. Homework 1, due Wednesday 2/24. Solutions. Pinhole cameras.
  2. Homework 2, due Wednesday 3/2. Solutions. Timing results.
  3. Homework 3, due Wednesday 3/9 and Friday 3/11. Solutions.
  4. Homework 4, due Friday 3/18. Solutions.
  5. Homework 5, due Friday 3/25. Solutions.
  6. Homework 6, due Wednesday 4/6. Solutions.
  7. Homework 7, due Friday 4/15. Solutions + timing results.
  8. Homework 8, due Monday 4/25. Solutions. Stereo ranking results.
  9. Homework 9, due Monday 5/2. Solutions. SFM results.
  10. Final project and list of projects. Final reports due Monday, 5/16.

Lectures & Readings

  1. M 2/15 - Course info, introduction to computer vision (Sz 1; optical illusions)
  2. W 2/17 - Image formation, perspective projection, image library (Sz 2; HW 1; links)
  3. F  2/19 - Ideal vs. real images, image formats, run-encoding (SS 2.3-5; imperfect images)
  4. M 2/22 - Binary image analysis, filtering, connected components (SS 3.1-4; Sz 3.3.4)
  5. W 2/24 - Binary morphology (SS 3.5; Sz 3.3.2)
  6. M 2/29 - Noise, box filter, Gaussian smoothing (TV 2.3.3; Sz 3.2.3)
  7. W 3/2   - Edge detection, image gradients, difference operators (Sz 4.2.1; TV 4)
  8. F  3/4   - Animal vision (Felix), HDR imaging (Joey), Laplacian and Marr-Hildreth edge detector (Sz 4.2.1; TV 4.2)
  9. M 3/7   - Canny edge detector, edge detection summary, Hough transform (Sz 4.2.1-2, 4.3.2; TV 4)
  10. W 3/9   - Hough transform, least-squares fitting (Sz 4.3.2, A2; TV 5.2; SS 10.3.4, MathWorld)
  11. F  3/11 - Image matting (Peter), HW 4 code (Sz 10.2)
  12. M 3/14 - Color (Sz 2.3.2; SS 6.1-4)
  13. W 3/16 - Image stabilization (Jordan), Feature detection and matching (Ben), geometric transforms (Sz. 4.1.1-3, 2.1.2)
  14. F  3/18 - JPEG encoding (Kevin), image warping, interpolation (Sz 5.1.1, 3.6.1)
  15. M 3/21 - Image compositing, homogeneous coordinates, homographies (Sz 3.1.3, 2.1.1-3)
  16. W 3/23 - 3D vision, projection matrix, intrinsic vs. extrinsic camera parameters (Sz 10.5, 2.1.5)
  17. F  3/25 - Camera calibration (Sz 2.1.5; TV 6.1, 6.3.1), Line labeling (Shannon), Texture synthesis (Dylan)
  18. M 4/4   - Exam info, camera calibration, SVD (TV 6.3.1, Sz A.1.1)
  19. W 4/6   - Exam review, intro to stereo (Sch 1.2, Sz 11.1)
  20. F  4/8   - Epipolar geometry, local correspondence, SSD (Sch 1.2, Sz 11.1, 11.3-4, stereo talk)
  21. M 4/11 - Stereo: SSD, SAD, NCC, disparity space (Sch 5.2, 6.1)
  22. W 4/13 - Middlebury Stereo Page, robust matching, shiftable windows, adaptive weights, cross-checking, imdiff app
  23. M 4/18 - Global matching, SGM stereo (Sz 3.7.2, 5.5, 11.5, Middlebury MRF page)
  24. W 4/20 - Video - Human-centric image understanding
  25. F  4/22 - Shape from shading (Zale); stereo cross checking; structured light (Sz 12.1-2, stereo talk)
  26. M 4/25 - Shape from defocus (Sebastian), Feature tracking (Vaasu), motion, optical flow (Sz 4.1.4, 5, 8.4; SS 9.3.4; Middlebury flow page)
  27. W 4/27 - Tomasi and Kanade's SFM factorization method (Sz 7.3, A.1.1, paper, video)
  28. F  4/29 - Intro to OpenCV
  29. M 5/2   - Final project info, optical flow, intro to recognition (Sz 8.1.3, 8.4, 14; CVPR tutorial)
  30. W 5/4   - Object recognition with CNNs (Max), more recognition (Sz 14; UW CS576 slides: Object recognition)
  31. F  5/6   - Face detection (Sam), principal component matching, "Eigenfaces" (Sz 14.1-2, UW CS576 slides: Face recognition, Matlab demo)
  32. M 5/9   - Snakes (John), epipolar geometry (Sch 1.2)
  33. W 5/11 - Seam carving (Dana), Computational photography (slides by Rick Szeliski)
  34. F  5/13 - Final project demos
  35. M 5/16 - Course summary and final exam info

Books on 2-hour reserve: Shapiro & Stockman (SS); Trucco & Verri (TV); Forsyth & Ponce; Nalwa; Sonka, Hlavac, & Boyle.

Resources: