CS 453 - Spring 2013
Self-scheduled (pick up from my office door), Tuesday 5/14 - Friday 5/17.
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
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 Friday May 17.
Practice questions on epipolar geometry.
- Homework 1, due Wednesday, 2/20.
- Homework 2, due Wednesday, 2/27.
- Homework 3, due Friday 3/8.
- Homework 4, due Friday, 3/15.
- Homework 5, due Friday, 3/22.
- Homework 6, due Wednesday, 4/3.
- Homework 7, due Friday, 4/12.
- Homework 8, due Monday, 4/22.
Stereo ranking results.
- Homework 9, due Monday, 4/29.
- Final project.
Lectures & Readings
- M 2/11 - Course info, introduction to computer vision (Sz 1)
- W 2/13 - Image formation, perspective projection, image library (Sz 2; HW 1)
- M 2/18 - Ideal vs. real images, run-encoding (SS 2.3-5)
- W 2/20 - Binary image analysis, filtering, connected components (SS 3.1-4; Sz 3.3.4)
- F 2/22 - Binary morphology, noise and smoothing (SS 3.5; Sz 3.3.2, 3.2)
- M 2/25 - Noise estimation, Gaussian smoothing, edge detection (TV 2.3.3; Sz 3.2.3, 4.2.1)
- W 2/27 - Image gradients, difference operators, Laplacian, Marr-Hildreth edge detector (Sz 4.2.1; TV 4)
- F 3/1 -
Animal vision (Dan C.),
Canny edge detector, (Sz 4.2.1; TV 4.2)
- M 3/4 - Edge detection summary, Hough transform (Sz 4.2.2, 4.3.2; TV 4)
- W 3/6 - Hough transform, least-squares fitting (Sz 4.3.2, A2; TV 5.2; SS 10.3.4,
- F 3/8 - HDR imaging (Miriam),
HW 4 code (Sz 10.2)
- M 3/11 - Color (Sz 2.3.2; SS 6.1-4)
- W 3/13 - Feature detection and matching (Colby),
geometric transforms (Sz. 4.1.1-3, 2.1.2)
- F 3/15 - Active contours / snakes (Nera),
image warping, interpolation (Sz 5.1.1, 3.6.1)
- M 3/18 - Image compositing, homogeneous coordinates, homographies (Sz 3.1.3, 2.1.1-3)
- W 3/20 - Texture synthesis (Xi),
3D vision, projection matrix, camera parameters (Sz 10.5, 2.1.5)
- F 3/22 - JPEG and MPEG encoding (Paul),
intrinsic vs. extrinsic parameters, camera calibration (Sz 2.1.5; TV 6.1, 6.3.1)
- M 4/1 - Exam info, camera calibration, SVD (TV 6.3.1, Sz A.1.1)
- W 4/3 - Exam review, intro to stereo (Sch 1.2, Sz 11.1)
- F 4/5 - Epipolar geometry, local correspondence, SSD (Sch 1.2, Sz 11.1, 11.3-4)
- M 4/8 - Stereo: SSD, SAD, NCC, disparity space (Sch 5.2, 6.1)
- W 4/10 - Image stabilization (Dan T.),
Image matting (Greg),
Middlebury Stereo Page
- F 4/12 - Stereo: a robust matching, shiftable windows, adaptive weights, cross-checking
- M 4/15 - Global matching, MRF stereo,
dynamic programming stereo,
(Sz 3.7.2, 5.5, 11.5,
Middlebury MRF page)
- W 4/17 - Image segmentation (Teddy),
motion, optical flow (Sz 5, 8.4; SS 9.3.4)
- M 4/22 - Feature tracking (Billy),
structured light, hidden texture (Sz 4.1.4, 12.2,
Middlebury flow page)
- W 4/24 - Tomasi and Kanade's SFM factorization method (Sz 7.3, A.1.1,
- F 4/26 - Intro to OpenCV
- M 4/29 - Final project info,
Intro to Recognition (Sz 14,
UW CS576 slides:
Object recognition and
- W 5/1 -
Shape from shading/texture (Matei),
Shape from focus/defocus (Dew)
Shape-from-X, (Sz 12.1,
- F 5/3 - Face detection, principal component matching, "Eigenfaces"
UW CS576 slides:
- M 5/6 - Lab day
- W 5/8 - Computational photography (slides by Rick Szeliski)
- F 5/10 - Final project demos
- M 5/13 - Course summary and final exam info
Books on 2-hour reserve:
Shapiro & Stockman (SS);
Trucco & Verri (TV);
Forsyth & Ponce;
Sonka, Hlavac, & Boyle.